[GIT pull] core/urgent for 5.7-rc2

[GIT pull] core/urgent for 5.7-rc2

[Thomas Gleixner]

Linus,

please pull the latest core/urgent branch from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git core-urgent-2020-04-19

up to:  40e7d7bdc19e: Merge branch 'urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu into core/urgent


A single bugfix for RCU to prevent taking a lock in NMI context.

Thanks,

	tglx

------------------>
Paul E. McKenney (1):
      rcu: Don't acquire lock in NMI handler in rcu_nmi_enter_common()


 kernel/rcu/tree.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 06548e2ebb72..d9a49cd6065a 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -825,7 +825,7 @@ static __always_inline void rcu_nmi_enter_common(bool irq)
 			rcu_cleanup_after_idle();
 
 		incby = 1;
-	} else if (tick_nohz_full_cpu(rdp->cpu) &&
+	} else if (irq && tick_nohz_full_cpu(rdp->cpu) &&
 		   rdp->dynticks_nmi_nesting == DYNTICK_IRQ_NONIDLE &&
 		   READ_ONCE(rdp->rcu_urgent_qs) &&
 		   !READ_ONCE(rdp->rcu_forced_tick)) {

[GIT pull] irq/urgent for 5.7-rc2

[Thomas Gleixner]

Linus,

please pull the latest irq/urgent branch from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq-urgent-2020-04-19

up to:  b5963029d9e3: Merge tag 'irqchip-fixes-5.7-2' of git://git.kernel.org/pub/scm/linux/kernel/git/maz/arm-platforms into irq/urgent


A set of fixes/updates for the interrupt subsystem:

 - Remove setup_irq() and remove_irq(). All users have been converted so
   remove them before new users surface.

 - A set of bugfixes for various interrupt chip drivers

 - Add a few missing static attributes to address sparse warnings.

Thanks,

	tglx

------------------>
Atish Patra (1):
      irqchip/sifive-plic: Fix maximum priority threshold value

Grygorii Strashko (1):
      irqchip/ti-sci-inta: Fix processing of masked irqs

Jason Yan (2):
      irqchip/irq-mvebu-icu: Make legacy_bindings static
      irqchip/irq-bcm7038-l1: Make bcm7038_l1_of_init() static

Marc Zyngier (3):
      irqchip/gic-v4.1: Add support for VPENDBASER's Dirty+Valid signaling
      irqchip/gic-v4.1: Update effective affinity of virtual SGIs
      irqchip/meson-gpio: Fix HARDIRQ-safe -> HARDIRQ-unsafe lock order

Zenghui Yu (1):
      irqchip/mbigen: Free msi_desc on device teardown

afzal mohammed (1):
      genirq: Remove setup_irq() and remove_irq()


 drivers/irqchip/irq-bcm7038-l1.c   |  2 +-
 drivers/irqchip/irq-gic-v3-its.c   | 20 +++++++++++++++++
 drivers/irqchip/irq-gic-v3.c       | 11 ++++++----
 drivers/irqchip/irq-mbigen.c       |  8 ++++++-
 drivers/irqchip/irq-meson-gpio.c   | 18 +++++++++-------
 drivers/irqchip/irq-mvebu-icu.c    |  2 +-
 drivers/irqchip/irq-sifive-plic.c  |  2 +-
 drivers/irqchip/irq-ti-sci-inta.c  |  3 ++-
 include/linux/irq.h                |  2 --
 include/linux/irqchip/arm-gic-v3.h |  2 ++
 kernel/irq/manage.c                | 44 --------------------------------------
 11 files changed, 51 insertions(+), 63 deletions(-)

diff --git a/drivers/irqchip/irq-bcm7038-l1.c b/drivers/irqchip/irq-bcm7038-l1.c
index eb9bce93cd05..fd7c537fb42a 100644
--- a/drivers/irqchip/irq-bcm7038-l1.c
+++ b/drivers/irqchip/irq-bcm7038-l1.c
@@ -416,7 +416,7 @@ static const struct irq_domain_ops bcm7038_l1_domain_ops = {
 	.map			= bcm7038_l1_map,
 };
 
-int __init bcm7038_l1_of_init(struct device_node *dn,
+static int __init bcm7038_l1_of_init(struct device_node *dn,
 			      struct device_node *parent)
 {
 	struct bcm7038_l1_chip *intc;
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 54d142ccc63a..124251b0ccba 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -14,6 +14,7 @@
 #include <linux/dma-iommu.h>
 #include <linux/efi.h>
 #include <linux/interrupt.h>
+#include <linux/iopoll.h>
 #include <linux/irqdomain.h>
 #include <linux/list.h>
 #include <linux/log2.h>
@@ -3672,6 +3673,20 @@ static int its_vpe_set_affinity(struct irq_data *d,
 	return IRQ_SET_MASK_OK_DONE;
 }
 
+static void its_wait_vpt_parse_complete(void)
+{
+	void __iomem *vlpi_base = gic_data_rdist_vlpi_base();
+	u64 val;
+
+	if (!gic_rdists->has_vpend_valid_dirty)
+		return;
+
+	WARN_ON_ONCE(readq_relaxed_poll_timeout(vlpi_base + GICR_VPENDBASER,
+						val,
+						!(val & GICR_VPENDBASER_Dirty),
+						10, 500));
+}
+
 static void its_vpe_schedule(struct its_vpe *vpe)
 {
 	void __iomem *vlpi_base = gic_data_rdist_vlpi_base();
@@ -3702,6 +3717,8 @@ static void its_vpe_schedule(struct its_vpe *vpe)
 	val |= vpe->idai ? GICR_VPENDBASER_IDAI : 0;
 	val |= GICR_VPENDBASER_Valid;
 	gicr_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER);
+
+	its_wait_vpt_parse_complete();
 }
 
 static void its_vpe_deschedule(struct its_vpe *vpe)
@@ -3910,6 +3927,8 @@ static void its_vpe_4_1_schedule(struct its_vpe *vpe,
 	val |= FIELD_PREP(GICR_VPENDBASER_4_1_VPEID, vpe->vpe_id);
 
 	gicr_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER);
+
+	its_wait_vpt_parse_complete();
 }
 
 static void its_vpe_4_1_deschedule(struct its_vpe *vpe,
@@ -4035,6 +4054,7 @@ static int its_sgi_set_affinity(struct irq_data *d,
 	 * not on the host (since they can only be targetting a vPE).
 	 * Tell the kernel we've done whatever it asked for.
 	 */
+	irq_data_update_effective_affinity(d, mask_val);
 	return IRQ_SET_MASK_OK;
 }
 
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 9dbc81b6f62e..d7006ef18a0d 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -873,6 +873,7 @@ static int __gic_update_rdist_properties(struct redist_region *region,
 	gic_data.rdists.has_rvpeid &= !!(typer & GICR_TYPER_RVPEID);
 	gic_data.rdists.has_direct_lpi &= (!!(typer & GICR_TYPER_DirectLPIS) |
 					   gic_data.rdists.has_rvpeid);
+	gic_data.rdists.has_vpend_valid_dirty &= !!(typer & GICR_TYPER_DIRTY);
 
 	/* Detect non-sensical configurations */
 	if (WARN_ON_ONCE(gic_data.rdists.has_rvpeid && !gic_data.rdists.has_vlpis)) {
@@ -893,10 +894,11 @@ static void gic_update_rdist_properties(void)
 	if (WARN_ON(gic_data.ppi_nr == UINT_MAX))
 		gic_data.ppi_nr = 0;
 	pr_info("%d PPIs implemented\n", gic_data.ppi_nr);
-	pr_info("%sVLPI support, %sdirect LPI support, %sRVPEID support\n",
-		!gic_data.rdists.has_vlpis ? "no " : "",
-		!gic_data.rdists.has_direct_lpi ? "no " : "",
-		!gic_data.rdists.has_rvpeid ? "no " : "");
+	if (gic_data.rdists.has_vlpis)
+		pr_info("GICv4 features: %s%s%s\n",
+			gic_data.rdists.has_direct_lpi ? "DirectLPI " : "",
+			gic_data.rdists.has_rvpeid ? "RVPEID " : "",
+			gic_data.rdists.has_vpend_valid_dirty ? "Valid+Dirty " : "");
 }
 
 /* Check whether it's single security state view */
@@ -1620,6 +1622,7 @@ static int __init gic_init_bases(void __iomem *dist_base,
 	gic_data.rdists.has_rvpeid = true;
 	gic_data.rdists.has_vlpis = true;
 	gic_data.rdists.has_direct_lpi = true;
+	gic_data.rdists.has_vpend_valid_dirty = true;
 
 	if (WARN_ON(!gic_data.domain) || WARN_ON(!gic_data.rdists.rdist)) {
 		err = -ENOMEM;
diff --git a/drivers/irqchip/irq-mbigen.c b/drivers/irqchip/irq-mbigen.c
index 6b566bba263b..ff7627b57772 100644
--- a/drivers/irqchip/irq-mbigen.c
+++ b/drivers/irqchip/irq-mbigen.c
@@ -220,10 +220,16 @@ static int mbigen_irq_domain_alloc(struct irq_domain *domain,
 	return 0;
 }
 
+static void mbigen_irq_domain_free(struct irq_domain *domain, unsigned int virq,
+				   unsigned int nr_irqs)
+{
+	platform_msi_domain_free(domain, virq, nr_irqs);
+}
+
 static const struct irq_domain_ops mbigen_domain_ops = {
 	.translate	= mbigen_domain_translate,
 	.alloc		= mbigen_irq_domain_alloc,
-	.free		= irq_domain_free_irqs_common,
+	.free		= mbigen_irq_domain_free,
 };
 
 static int mbigen_of_create_domain(struct platform_device *pdev,
diff --git a/drivers/irqchip/irq-meson-gpio.c b/drivers/irqchip/irq-meson-gpio.c
index ccc7f823911b..bc7aebcc96e9 100644
--- a/drivers/irqchip/irq-meson-gpio.c
+++ b/drivers/irqchip/irq-meson-gpio.c
@@ -144,12 +144,17 @@ struct meson_gpio_irq_controller {
 static void meson_gpio_irq_update_bits(struct meson_gpio_irq_controller *ctl,
 				       unsigned int reg, u32 mask, u32 val)
 {
+	unsigned long flags;
 	u32 tmp;
 
+	spin_lock_irqsave(&ctl->lock, flags);
+
 	tmp = readl_relaxed(ctl->base + reg);
 	tmp &= ~mask;
 	tmp |= val;
 	writel_relaxed(tmp, ctl->base + reg);
+
+	spin_unlock_irqrestore(&ctl->lock, flags);
 }
 
 static void meson_gpio_irq_init_dummy(struct meson_gpio_irq_controller *ctl)
@@ -196,14 +201,15 @@ meson_gpio_irq_request_channel(struct meson_gpio_irq_controller *ctl,
 			       unsigned long  hwirq,
 			       u32 **channel_hwirq)
 {
+	unsigned long flags;
 	unsigned int idx;
 
-	spin_lock(&ctl->lock);
+	spin_lock_irqsave(&ctl->lock, flags);
 
 	/* Find a free channel */
 	idx = find_first_zero_bit(ctl->channel_map, NUM_CHANNEL);
 	if (idx >= NUM_CHANNEL) {
-		spin_unlock(&ctl->lock);
+		spin_unlock_irqrestore(&ctl->lock, flags);
 		pr_err("No channel available\n");
 		return -ENOSPC;
 	}
@@ -211,6 +217,8 @@ meson_gpio_irq_request_channel(struct meson_gpio_irq_controller *ctl,
 	/* Mark the channel as used */
 	set_bit(idx, ctl->channel_map);
 
+	spin_unlock_irqrestore(&ctl->lock, flags);
+
 	/*
 	 * Setup the mux of the channel to route the signal of the pad
 	 * to the appropriate input of the GIC
@@ -225,8 +233,6 @@ meson_gpio_irq_request_channel(struct meson_gpio_irq_controller *ctl,
 	 */
 	*channel_hwirq = &(ctl->channel_irqs[idx]);
 
-	spin_unlock(&ctl->lock);
-
 	pr_debug("hwirq %lu assigned to channel %d - irq %u\n",
 		 hwirq, idx, **channel_hwirq);
 
@@ -287,13 +293,9 @@ static int meson_gpio_irq_type_setup(struct meson_gpio_irq_controller *ctl,
 			val |= REG_EDGE_POL_LOW(params, idx);
 	}
 
-	spin_lock(&ctl->lock);
-
 	meson_gpio_irq_update_bits(ctl, REG_EDGE_POL,
 				   REG_EDGE_POL_MASK(params, idx), val);
 
-	spin_unlock(&ctl->lock);
-
 	return 0;
 }
 
diff --git a/drivers/irqchip/irq-mvebu-icu.c b/drivers/irqchip/irq-mvebu-icu.c
index 547045d89c4b..91adf771f185 100644
--- a/drivers/irqchip/irq-mvebu-icu.c
+++ b/drivers/irqchip/irq-mvebu-icu.c
@@ -66,7 +66,7 @@ struct mvebu_icu_irq_data {
 	unsigned int type;
 };
 
-DEFINE_STATIC_KEY_FALSE(legacy_bindings);
+static DEFINE_STATIC_KEY_FALSE(legacy_bindings);
 
 static void mvebu_icu_init(struct mvebu_icu *icu,
 			   struct mvebu_icu_msi_data *msi_data,
diff --git a/drivers/irqchip/irq-sifive-plic.c b/drivers/irqchip/irq-sifive-plic.c
index c34fb3ae0ff8..d0a71febdadc 100644
--- a/drivers/irqchip/irq-sifive-plic.c
+++ b/drivers/irqchip/irq-sifive-plic.c
@@ -56,7 +56,7 @@
 #define     CONTEXT_THRESHOLD		0x00
 #define     CONTEXT_CLAIM		0x04
 
-#define	PLIC_DISABLE_THRESHOLD		0xf
+#define	PLIC_DISABLE_THRESHOLD		0x7
 #define	PLIC_ENABLE_THRESHOLD		0
 
 struct plic_priv {
diff --git a/drivers/irqchip/irq-ti-sci-inta.c b/drivers/irqchip/irq-ti-sci-inta.c
index 8f6e6b08eadf..7e3ebf6ed2cd 100644
--- a/drivers/irqchip/irq-ti-sci-inta.c
+++ b/drivers/irqchip/irq-ti-sci-inta.c
@@ -37,6 +37,7 @@
 #define VINT_ENABLE_SET_OFFSET	0x0
 #define VINT_ENABLE_CLR_OFFSET	0x8
 #define VINT_STATUS_OFFSET	0x18
+#define VINT_STATUS_MASKED_OFFSET	0x20
 
 /**
  * struct ti_sci_inta_event_desc - Description of an event coming to
@@ -116,7 +117,7 @@ static void ti_sci_inta_irq_handler(struct irq_desc *desc)
 	chained_irq_enter(irq_desc_get_chip(desc), desc);
 
 	val = readq_relaxed(inta->base + vint_desc->vint_id * 0x1000 +
-			    VINT_STATUS_OFFSET);
+			    VINT_STATUS_MASKED_OFFSET);
 
 	for_each_set_bit(bit, &val, MAX_EVENTS_PER_VINT) {
 		virq = irq_find_mapping(domain, vint_desc->events[bit].hwirq);
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 9315fbb87db3..c63c2aa915ff 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -573,8 +573,6 @@ enum {
 #define IRQ_DEFAULT_INIT_FLAGS	ARCH_IRQ_INIT_FLAGS
 
 struct irqaction;
-extern int setup_irq(unsigned int irq, struct irqaction *new);
-extern void remove_irq(unsigned int irq, struct irqaction *act);
 extern int setup_percpu_irq(unsigned int irq, struct irqaction *new);
 extern void remove_percpu_irq(unsigned int irq, struct irqaction *act);
 
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 765d9b769b69..6c36b6cc3edf 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -243,6 +243,7 @@
 
 #define GICR_TYPER_PLPIS		(1U << 0)
 #define GICR_TYPER_VLPIS		(1U << 1)
+#define GICR_TYPER_DIRTY		(1U << 2)
 #define GICR_TYPER_DirectLPIS		(1U << 3)
 #define GICR_TYPER_LAST			(1U << 4)
 #define GICR_TYPER_RVPEID		(1U << 7)
@@ -686,6 +687,7 @@ struct rdists {
 	bool			has_vlpis;
 	bool			has_rvpeid;
 	bool			has_direct_lpi;
+	bool			has_vpend_valid_dirty;
 };
 
 struct irq_domain;
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index fe40c658f86f..453a8a0f4804 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1690,34 +1690,6 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 	return ret;
 }
 
-/**
- *	setup_irq - setup an interrupt
- *	@irq: Interrupt line to setup
- *	@act: irqaction for the interrupt
- *
- * Used to statically setup interrupts in the early boot process.
- */
-int setup_irq(unsigned int irq, struct irqaction *act)
-{
-	int retval;
-	struct irq_desc *desc = irq_to_desc(irq);
-
-	if (!desc || WARN_ON(irq_settings_is_per_cpu_devid(desc)))
-		return -EINVAL;
-
-	retval = irq_chip_pm_get(&desc->irq_data);
-	if (retval < 0)
-		return retval;
-
-	retval = __setup_irq(irq, desc, act);
-
-	if (retval)
-		irq_chip_pm_put(&desc->irq_data);
-
-	return retval;
-}
-EXPORT_SYMBOL_GPL(setup_irq);
-
 /*
  * Internal function to unregister an irqaction - used to free
  * regular and special interrupts that are part of the architecture.
@@ -1858,22 +1830,6 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
 	return action;
 }
 
-/**
- *	remove_irq - free an interrupt
- *	@irq: Interrupt line to free
- *	@act: irqaction for the interrupt
- *
- * Used to remove interrupts statically setup by the early boot process.
- */
-void remove_irq(unsigned int irq, struct irqaction *act)
-{
-	struct irq_desc *desc = irq_to_desc(irq);
-
-	if (desc && !WARN_ON(irq_settings_is_per_cpu_devid(desc)))
-		__free_irq(desc, act->dev_id);
-}
-EXPORT_SYMBOL_GPL(remove_irq);
-
 /**
  *	free_irq - free an interrupt allocated with request_irq
  *	@irq: Interrupt line to free

Re: [GIT pull] irq/urgent for 5.7-rc2

[pr-tracker-bot]

The pull request you sent on Sun, 19 Apr 2020 13:56:39 -0000:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq-urgent-2020-04-19

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/80ade29e1ed0d04fdb108b2344f27b89997fc408

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

[GIT pull] perf/urgent for 5.7-rc2

[Thomas Gleixner]

Linus,

please pull the latest perf/urgent branch from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2020-04-19

up to:  cd0943357bc7: Merge tag 'perf-urgent-for-mingo-5.7-20200414' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent


Perf updates and fixes:

 - Fix the header line of perf stat output for '--metric-only --per-socket'

 - Fix the python build with clang

 - The usual tools UAPI header synchronization

Thanks,

	tglx

------------------>
Arnaldo Carvalho de Melo (14):
      tools arch x86: Sync the msr-index.h copy with the kernel sources
      perf python: Check if clang supports -fno-semantic-interposition
      tools headers: Update linux/vdso.h and grab a copy of vdso/const.h
      tools headers UAPI: Sync sched.h with the kernel
      tools headers UAPI: Sync linux/mman.h with the kernel
      tools arch x86: Sync asm/cpufeatures.h with the kernel sources
      tools include UAPI: Sync linux/vhost.h with the kernel sources
      tools headers UAPI: Sync linux/fscrypt.h with the kernel sources
      tools headers kvm: Sync linux/kvm.h with the kernel sources
      tools headers UAPI: Update tools's copy of drm.h headers
      tools headers UAPI: Sync drm/i915_drm.h with the kernel sources
      tools headers: Update x86's syscall_64.tbl with the kernel sources
      tools headers: Adopt verbatim copy of compiletime_assert() from kernel sources
      tools headers: Synchronize linux/bits.h with the kernel sources

Jin Yao (1):
      perf stat: Fix no metric header if --per-socket and --metric-only set


 tools/arch/x86/include/asm/cpufeatures.h          |   5 +-
 tools/arch/x86/include/asm/msr-index.h            |   9 +
 tools/include/linux/bits.h                        |  24 +-
 tools/include/linux/build_bug.h                   |  82 +++
 tools/include/linux/compiler.h                    |  26 +
 tools/include/linux/const.h                       |   5 +-
 tools/include/linux/kernel.h                      |   4 +-
 tools/include/uapi/drm/drm.h                      |   2 +
 tools/include/uapi/drm/i915_drm.h                 |  21 +
 tools/include/uapi/linux/fscrypt.h                |   1 +
 tools/include/uapi/linux/kvm.h                    |  47 +-
 tools/include/uapi/linux/mman.h                   |   5 +-
 tools/include/uapi/linux/sched.h                  |   5 +
 tools/include/uapi/linux/vhost.h                  |  24 +
 tools/include/vdso/bits.h                         |   9 +
 tools/include/vdso/const.h                        |  10 +
 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl | 740 +++++++++++-----------
 tools/perf/check-headers.sh                       |   3 +
 tools/perf/trace/beauty/clone.c                   |   1 +
 tools/perf/trace/beauty/mmap.c                    |   1 +
 tools/perf/util/setup.py                          |   2 +
 tools/perf/util/stat-shadow.c                     |   7 +-
 22 files changed, 646 insertions(+), 387 deletions(-)
 create mode 100644 tools/include/linux/build_bug.h
 create mode 100644 tools/include/vdso/bits.h
 create mode 100644 tools/include/vdso/const.h

diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index f3327cb56edf..db189945e9b0 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -217,7 +217,7 @@
 #define X86_FEATURE_IBRS		( 7*32+25) /* Indirect Branch Restricted Speculation */
 #define X86_FEATURE_IBPB		( 7*32+26) /* Indirect Branch Prediction Barrier */
 #define X86_FEATURE_STIBP		( 7*32+27) /* Single Thread Indirect Branch Predictors */
-#define X86_FEATURE_ZEN			( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */
+#define X86_FEATURE_ZEN			( 7*32+28) /* "" CPU is AMD family 0x17 or above (Zen) */
 #define X86_FEATURE_L1TF_PTEINV		( 7*32+29) /* "" L1TF workaround PTE inversion */
 #define X86_FEATURE_IBRS_ENHANCED	( 7*32+30) /* Enhanced IBRS */
 #define X86_FEATURE_MSR_IA32_FEAT_CTL	( 7*32+31) /* "" MSR IA32_FEAT_CTL configured */
@@ -285,6 +285,7 @@
 #define X86_FEATURE_CQM_MBM_LOCAL	(11*32+ 3) /* LLC Local MBM monitoring */
 #define X86_FEATURE_FENCE_SWAPGS_USER	(11*32+ 4) /* "" LFENCE in user entry SWAPGS path */
 #define X86_FEATURE_FENCE_SWAPGS_KERNEL	(11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */
+#define X86_FEATURE_SPLIT_LOCK_DETECT	(11*32+ 6) /* #AC for split lock */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX512_BF16		(12*32+ 5) /* AVX512 BFLOAT16 instructions */
@@ -299,6 +300,7 @@
 #define X86_FEATURE_AMD_IBRS		(13*32+14) /* "" Indirect Branch Restricted Speculation */
 #define X86_FEATURE_AMD_STIBP		(13*32+15) /* "" Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_AMD_STIBP_ALWAYS_ON	(13*32+17) /* "" Single Thread Indirect Branch Predictors always-on preferred */
+#define X86_FEATURE_AMD_PPIN		(13*32+23) /* Protected Processor Inventory Number */
 #define X86_FEATURE_AMD_SSBD		(13*32+24) /* "" Speculative Store Bypass Disable */
 #define X86_FEATURE_VIRT_SSBD		(13*32+25) /* Virtualized Speculative Store Bypass Disable */
 #define X86_FEATURE_AMD_SSB_NO		(13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */
@@ -367,6 +369,7 @@
 #define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_FLUSH_L1D		(18*32+28) /* Flush L1D cache */
 #define X86_FEATURE_ARCH_CAPABILITIES	(18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
+#define X86_FEATURE_CORE_CAPABILITIES	(18*32+30) /* "" IA32_CORE_CAPABILITIES MSR */
 #define X86_FEATURE_SPEC_CTRL_SSBD	(18*32+31) /* "" Speculative Store Bypass Disable */
 
 /*
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index d5e517d1c3dd..12c9684d59ba 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -41,6 +41,10 @@
 
 /* Intel MSRs. Some also available on other CPUs */
 
+#define MSR_TEST_CTRL				0x00000033
+#define MSR_TEST_CTRL_SPLIT_LOCK_DETECT_BIT	29
+#define MSR_TEST_CTRL_SPLIT_LOCK_DETECT		BIT(MSR_TEST_CTRL_SPLIT_LOCK_DETECT_BIT)
+
 #define MSR_IA32_SPEC_CTRL		0x00000048 /* Speculation Control */
 #define SPEC_CTRL_IBRS			BIT(0)	   /* Indirect Branch Restricted Speculation */
 #define SPEC_CTRL_STIBP_SHIFT		1	   /* Single Thread Indirect Branch Predictor (STIBP) bit */
@@ -70,6 +74,11 @@
  */
 #define MSR_IA32_UMWAIT_CONTROL_TIME_MASK	(~0x03U)
 
+/* Abbreviated from Intel SDM name IA32_CORE_CAPABILITIES */
+#define MSR_IA32_CORE_CAPS			  0x000000cf
+#define MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT_BIT  5
+#define MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT	  BIT(MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT_BIT)
+
 #define MSR_PKG_CST_CONFIG_CONTROL	0x000000e2
 #define NHM_C3_AUTO_DEMOTE		(1UL << 25)
 #define NHM_C1_AUTO_DEMOTE		(1UL << 26)
diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h
index 669d69441a62..4671fbf28842 100644
--- a/tools/include/linux/bits.h
+++ b/tools/include/linux/bits.h
@@ -3,9 +3,9 @@
 #define __LINUX_BITS_H
 
 #include <linux/const.h>
+#include <vdso/bits.h>
 #include <asm/bitsperlong.h>
 
-#define BIT(nr)			(UL(1) << (nr))
 #define BIT_ULL(nr)		(ULL(1) << (nr))
 #define BIT_MASK(nr)		(UL(1) << ((nr) % BITS_PER_LONG))
 #define BIT_WORD(nr)		((nr) / BITS_PER_LONG)
@@ -18,12 +18,30 @@
  * position @h. For example
  * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
  */
-#define GENMASK(h, l) \
+#if !defined(__ASSEMBLY__) && \
+	(!defined(CONFIG_CC_IS_GCC) || CONFIG_GCC_VERSION >= 49000)
+#include <linux/build_bug.h>
+#define GENMASK_INPUT_CHECK(h, l) \
+	(BUILD_BUG_ON_ZERO(__builtin_choose_expr( \
+		__builtin_constant_p((l) > (h)), (l) > (h), 0)))
+#else
+/*
+ * BUILD_BUG_ON_ZERO is not available in h files included from asm files,
+ * disable the input check if that is the case.
+ */
+#define GENMASK_INPUT_CHECK(h, l) 0
+#endif
+
+#define __GENMASK(h, l) \
 	(((~UL(0)) - (UL(1) << (l)) + 1) & \
 	 (~UL(0) >> (BITS_PER_LONG - 1 - (h))))
+#define GENMASK(h, l) \
+	(GENMASK_INPUT_CHECK(h, l) + __GENMASK(h, l))
 
-#define GENMASK_ULL(h, l) \
+#define __GENMASK_ULL(h, l) \
 	(((~ULL(0)) - (ULL(1) << (l)) + 1) & \
 	 (~ULL(0) >> (BITS_PER_LONG_LONG - 1 - (h))))
+#define GENMASK_ULL(h, l) \
+	(GENMASK_INPUT_CHECK(h, l) + __GENMASK_ULL(h, l))
 
 #endif	/* __LINUX_BITS_H */
diff --git a/tools/include/linux/build_bug.h b/tools/include/linux/build_bug.h
new file mode 100644
index 000000000000..cc7070c7439b
--- /dev/null
+++ b/tools/include/linux/build_bug.h
@@ -0,0 +1,82 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_BUILD_BUG_H
+#define _LINUX_BUILD_BUG_H
+
+#include <linux/compiler.h>
+
+#ifdef __CHECKER__
+#define BUILD_BUG_ON_ZERO(e) (0)
+#else /* __CHECKER__ */
+/*
+ * Force a compilation error if condition is true, but also produce a
+ * result (of value 0 and type int), so the expression can be used
+ * e.g. in a structure initializer (or where-ever else comma expressions
+ * aren't permitted).
+ */
+#define BUILD_BUG_ON_ZERO(e) ((int)(sizeof(struct { int:(-!!(e)); })))
+#endif /* __CHECKER__ */
+
+/* Force a compilation error if a constant expression is not a power of 2 */
+#define __BUILD_BUG_ON_NOT_POWER_OF_2(n)	\
+	BUILD_BUG_ON(((n) & ((n) - 1)) != 0)
+#define BUILD_BUG_ON_NOT_POWER_OF_2(n)			\
+	BUILD_BUG_ON((n) == 0 || (((n) & ((n) - 1)) != 0))
+
+/*
+ * BUILD_BUG_ON_INVALID() permits the compiler to check the validity of the
+ * expression but avoids the generation of any code, even if that expression
+ * has side-effects.
+ */
+#define BUILD_BUG_ON_INVALID(e) ((void)(sizeof((__force long)(e))))
+
+/**
+ * BUILD_BUG_ON_MSG - break compile if a condition is true & emit supplied
+ *		      error message.
+ * @condition: the condition which the compiler should know is false.
+ *
+ * See BUILD_BUG_ON for description.
+ */
+#define BUILD_BUG_ON_MSG(cond, msg) compiletime_assert(!(cond), msg)
+
+/**
+ * BUILD_BUG_ON - break compile if a condition is true.
+ * @condition: the condition which the compiler should know is false.
+ *
+ * If you have some code which relies on certain constants being equal, or
+ * some other compile-time-evaluated condition, you should use BUILD_BUG_ON to
+ * detect if someone changes it.
+ */
+#define BUILD_BUG_ON(condition) \
+	BUILD_BUG_ON_MSG(condition, "BUILD_BUG_ON failed: " #condition)
+
+/**
+ * BUILD_BUG - break compile if used.
+ *
+ * If you have some code that you expect the compiler to eliminate at
+ * build time, you should use BUILD_BUG to detect if it is
+ * unexpectedly used.
+ */
+#define BUILD_BUG() BUILD_BUG_ON_MSG(1, "BUILD_BUG failed")
+
+/**
+ * static_assert - check integer constant expression at build time
+ *
+ * static_assert() is a wrapper for the C11 _Static_assert, with a
+ * little macro magic to make the message optional (defaulting to the
+ * stringification of the tested expression).
+ *
+ * Contrary to BUILD_BUG_ON(), static_assert() can be used at global
+ * scope, but requires the expression to be an integer constant
+ * expression (i.e., it is not enough that __builtin_constant_p() is
+ * true for expr).
+ *
+ * Also note that BUILD_BUG_ON() fails the build if the condition is
+ * true, while static_assert() fails the build if the expression is
+ * false.
+ */
+#ifndef static_assert
+#define static_assert(expr, ...) __static_assert(expr, ##__VA_ARGS__, #expr)
+#define __static_assert(expr, msg, ...) _Static_assert(expr, msg)
+#endif // static_assert
+
+#endif	/* _LINUX_BUILD_BUG_H */
diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
index 1827c2f973f9..180f7714a5f1 100644
--- a/tools/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -10,6 +10,32 @@
 # define __compiletime_error(message)
 #endif
 
+#ifdef __OPTIMIZE__
+# define __compiletime_assert(condition, msg, prefix, suffix)		\
+	do {								\
+		extern void prefix ## suffix(void) __compiletime_error(msg); \
+		if (!(condition))					\
+			prefix ## suffix();				\
+	} while (0)
+#else
+# define __compiletime_assert(condition, msg, prefix, suffix) do { } while (0)
+#endif
+
+#define _compiletime_assert(condition, msg, prefix, suffix) \
+	__compiletime_assert(condition, msg, prefix, suffix)
+
+/**
+ * compiletime_assert - break build and emit msg if condition is false
+ * @condition: a compile-time constant condition to check
+ * @msg:       a message to emit if condition is false
+ *
+ * In tradition of POSIX assert, this macro will break the build if the
+ * supplied condition is *false*, emitting the supplied error message if the
+ * compiler has support to do so.
+ */
+#define compiletime_assert(condition, msg) \
+	_compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__)
+
 /* Optimization barrier */
 /* The "volatile" is due to gcc bugs */
 #define barrier() __asm__ __volatile__("": : :"memory")
diff --git a/tools/include/linux/const.h b/tools/include/linux/const.h
index 7b55a55f5911..81b8aae5a855 100644
--- a/tools/include/linux/const.h
+++ b/tools/include/linux/const.h
@@ -1,9 +1,6 @@
 #ifndef _LINUX_CONST_H
 #define _LINUX_CONST_H
 
-#include <uapi/linux/const.h>
-
-#define UL(x)		(_UL(x))
-#define ULL(x)		(_ULL(x))
+#include <vdso/const.h>
 
 #endif /* _LINUX_CONST_H */
diff --git a/tools/include/linux/kernel.h b/tools/include/linux/kernel.h
index cba226948a0c..a7e54a08fb54 100644
--- a/tools/include/linux/kernel.h
+++ b/tools/include/linux/kernel.h
@@ -5,6 +5,7 @@
 #include <stdarg.h>
 #include <stddef.h>
 #include <assert.h>
+#include <linux/build_bug.h>
 #include <linux/compiler.h>
 #include <endian.h>
 #include <byteswap.h>
@@ -35,9 +36,6 @@
 	(type *)((char *)__mptr - offsetof(type, member)); })
 #endif
 
-#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)]))
-#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:-!!(e); }))
-
 #ifndef max
 #define max(x, y) ({				\
 	typeof(x) _max1 = (x);			\
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index 868bf7996c0f..808b48a93330 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -948,6 +948,8 @@ extern "C" {
 #define DRM_IOCTL_SYNCOBJ_TRANSFER	DRM_IOWR(0xCC, struct drm_syncobj_transfer)
 #define DRM_IOCTL_SYNCOBJ_TIMELINE_SIGNAL	DRM_IOWR(0xCD, struct drm_syncobj_timeline_array)
 
+#define DRM_IOCTL_MODE_GETFB2		DRM_IOWR(0xCE, struct drm_mode_fb_cmd2)
+
 /**
  * Device specific ioctls should only be in their respective headers
  * The device specific ioctl range is from 0x40 to 0x9f.
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 829c0a48577f..2813e579b480 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -1619,6 +1619,27 @@ struct drm_i915_gem_context_param {
  * By default, new contexts allow persistence.
  */
 #define I915_CONTEXT_PARAM_PERSISTENCE	0xb
+
+/*
+ * I915_CONTEXT_PARAM_RINGSIZE:
+ *
+ * Sets the size of the CS ringbuffer to use for logical ring contexts. This
+ * applies a limit of how many batches can be queued to HW before the caller
+ * is blocked due to lack of space for more commands.
+ *
+ * Only reliably possible to be set prior to first use, i.e. during
+ * construction. At any later point, the current execution must be flushed as
+ * the ring can only be changed while the context is idle. Note, the ringsize
+ * can be specified as a constructor property, see
+ * I915_CONTEXT_CREATE_EXT_SETPARAM, but can also be set later if required.
+ *
+ * Only applies to the current set of engine and lost when those engines
+ * are replaced by a new mapping (see I915_CONTEXT_PARAM_ENGINES).
+ *
+ * Must be between 4 - 512 KiB, in intervals of page size [4 KiB].
+ * Default is 16 KiB.
+ */
+#define I915_CONTEXT_PARAM_RINGSIZE	0xc
 /* Must be kept compact -- no holes and well documented */
 
 	__u64 value;
diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h
index 0d8a6f47711c..a10e3cdc2839 100644
--- a/tools/include/uapi/linux/fscrypt.h
+++ b/tools/include/uapi/linux/fscrypt.h
@@ -163,6 +163,7 @@ struct fscrypt_get_key_status_arg {
 #define FS_IOC_REMOVE_ENCRYPTION_KEY		_IOWR('f', 24, struct fscrypt_remove_key_arg)
 #define FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS	_IOWR('f', 25, struct fscrypt_remove_key_arg)
 #define FS_IOC_GET_ENCRYPTION_KEY_STATUS	_IOWR('f', 26, struct fscrypt_get_key_status_arg)
+#define FS_IOC_GET_ENCRYPTION_NONCE		_IOR('f', 27, __u8[16])
 
 /**********************************************************************/
 
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 4b95f9a31a2f..428c7dde6b4b 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -474,12 +474,17 @@ struct kvm_s390_mem_op {
 	__u32 size;		/* amount of bytes */
 	__u32 op;		/* type of operation */
 	__u64 buf;		/* buffer in userspace */
-	__u8 ar;		/* the access register number */
-	__u8 reserved[31];	/* should be set to 0 */
+	union {
+		__u8 ar;	/* the access register number */
+		__u32 sida_offset; /* offset into the sida */
+		__u8 reserved[32]; /* should be set to 0 */
+	};
 };
 /* types for kvm_s390_mem_op->op */
 #define KVM_S390_MEMOP_LOGICAL_READ	0
 #define KVM_S390_MEMOP_LOGICAL_WRITE	1
+#define KVM_S390_MEMOP_SIDA_READ	2
+#define KVM_S390_MEMOP_SIDA_WRITE	3
 /* flags for kvm_s390_mem_op->flags */
 #define KVM_S390_MEMOP_F_CHECK_ONLY		(1ULL << 0)
 #define KVM_S390_MEMOP_F_INJECT_EXCEPTION	(1ULL << 1)
@@ -1010,6 +1015,8 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_ARM_NISV_TO_USER 177
 #define KVM_CAP_ARM_INJECT_EXT_DABT 178
 #define KVM_CAP_S390_VCPU_RESETS 179
+#define KVM_CAP_S390_PROTECTED 180
+#define KVM_CAP_PPC_SECURE_GUEST 181
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1478,6 +1485,39 @@ struct kvm_enc_region {
 #define KVM_S390_NORMAL_RESET	_IO(KVMIO,   0xc3)
 #define KVM_S390_CLEAR_RESET	_IO(KVMIO,   0xc4)
 
+struct kvm_s390_pv_sec_parm {
+	__u64 origin;
+	__u64 length;
+};
+
+struct kvm_s390_pv_unp {
+	__u64 addr;
+	__u64 size;
+	__u64 tweak;
+};
+
+enum pv_cmd_id {
+	KVM_PV_ENABLE,
+	KVM_PV_DISABLE,
+	KVM_PV_SET_SEC_PARMS,
+	KVM_PV_UNPACK,
+	KVM_PV_VERIFY,
+	KVM_PV_PREP_RESET,
+	KVM_PV_UNSHARE_ALL,
+};
+
+struct kvm_pv_cmd {
+	__u32 cmd;	/* Command to be executed */
+	__u16 rc;	/* Ultravisor return code */
+	__u16 rrc;	/* Ultravisor return reason code */
+	__u64 data;	/* Data or address */
+	__u32 flags;    /* flags for future extensions. Must be 0 for now */
+	__u32 reserved[3];
+};
+
+/* Available with KVM_CAP_S390_PROTECTED */
+#define KVM_S390_PV_COMMAND		_IOWR(KVMIO, 0xc5, struct kvm_pv_cmd)
+
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {
 	/* Guest initialization commands */
@@ -1628,4 +1668,7 @@ struct kvm_hyperv_eventfd {
 #define KVM_HYPERV_CONN_ID_MASK		0x00ffffff
 #define KVM_HYPERV_EVENTFD_DEASSIGN	(1 << 0)
 
+#define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE    (1 << 0)
+#define KVM_DIRTY_LOG_INITIALLY_SET            (1 << 1)
+
 #endif /* __LINUX_KVM_H */
diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h
index fc1a64c3447b..923cc162609c 100644
--- a/tools/include/uapi/linux/mman.h
+++ b/tools/include/uapi/linux/mman.h
@@ -5,8 +5,9 @@
 #include <asm/mman.h>
 #include <asm-generic/hugetlb_encode.h>
 
-#define MREMAP_MAYMOVE	1
-#define MREMAP_FIXED	2
+#define MREMAP_MAYMOVE		1
+#define MREMAP_FIXED		2
+#define MREMAP_DONTUNMAP	4
 
 #define OVERCOMMIT_GUESS		0
 #define OVERCOMMIT_ALWAYS		1
diff --git a/tools/include/uapi/linux/sched.h b/tools/include/uapi/linux/sched.h
index 2e3bc22c6f20..3bac0a8ceab2 100644
--- a/tools/include/uapi/linux/sched.h
+++ b/tools/include/uapi/linux/sched.h
@@ -35,6 +35,7 @@
 
 /* Flags for the clone3() syscall. */
 #define CLONE_CLEAR_SIGHAND 0x100000000ULL /* Clear any signal handler and reset to SIG_DFL. */
+#define CLONE_INTO_CGROUP 0x200000000ULL /* Clone into a specific cgroup given the right permissions. */
 
 /*
  * cloning flags intersect with CSIGNAL so can be used with unshare and clone3
@@ -81,6 +82,8 @@
  * @set_tid_size: This defines the size of the array referenced
  *                in @set_tid. This cannot be larger than the
  *                kernel's limit of nested PID namespaces.
+ * @cgroup:       If CLONE_INTO_CGROUP is specified set this to
+ *                a file descriptor for the cgroup.
  *
  * The structure is versioned by size and thus extensible.
  * New struct members must go at the end of the struct and
@@ -97,11 +100,13 @@ struct clone_args {
 	__aligned_u64 tls;
 	__aligned_u64 set_tid;
 	__aligned_u64 set_tid_size;
+	__aligned_u64 cgroup;
 };
 #endif
 
 #define CLONE_ARGS_SIZE_VER0 64 /* sizeof first published struct */
 #define CLONE_ARGS_SIZE_VER1 80 /* sizeof second published struct */
+#define CLONE_ARGS_SIZE_VER2 88 /* sizeof third published struct */
 
 /*
  * Scheduling policies
diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h
index 40d028eed645..9fe72e4b1373 100644
--- a/tools/include/uapi/linux/vhost.h
+++ b/tools/include/uapi/linux/vhost.h
@@ -116,4 +116,28 @@
 #define VHOST_VSOCK_SET_GUEST_CID	_IOW(VHOST_VIRTIO, 0x60, __u64)
 #define VHOST_VSOCK_SET_RUNNING		_IOW(VHOST_VIRTIO, 0x61, int)
 
+/* VHOST_VDPA specific defines */
+
+/* Get the device id. The device ids follow the same definition of
+ * the device id defined in virtio-spec.
+ */
+#define VHOST_VDPA_GET_DEVICE_ID	_IOR(VHOST_VIRTIO, 0x70, __u32)
+/* Get and set the status. The status bits follow the same definition
+ * of the device status defined in virtio-spec.
+ */
+#define VHOST_VDPA_GET_STATUS		_IOR(VHOST_VIRTIO, 0x71, __u8)
+#define VHOST_VDPA_SET_STATUS		_IOW(VHOST_VIRTIO, 0x72, __u8)
+/* Get and set the device config. The device config follows the same
+ * definition of the device config defined in virtio-spec.
+ */
+#define VHOST_VDPA_GET_CONFIG		_IOR(VHOST_VIRTIO, 0x73, \
+					     struct vhost_vdpa_config)
+#define VHOST_VDPA_SET_CONFIG		_IOW(VHOST_VIRTIO, 0x74, \
+					     struct vhost_vdpa_config)
+/* Enable/disable the ring. */
+#define VHOST_VDPA_SET_VRING_ENABLE	_IOW(VHOST_VIRTIO, 0x75, \
+					     struct vhost_vring_state)
+/* Get the max ring size. */
+#define VHOST_VDPA_GET_VRING_NUM	_IOR(VHOST_VIRTIO, 0x76, __u16)
+
 #endif
diff --git a/tools/include/vdso/bits.h b/tools/include/vdso/bits.h
new file mode 100644
index 000000000000..6d005a1f5d94
--- /dev/null
+++ b/tools/include/vdso/bits.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __VDSO_BITS_H
+#define __VDSO_BITS_H
+
+#include <vdso/const.h>
+
+#define BIT(nr)			(UL(1) << (nr))
+
+#endif	/* __VDSO_BITS_H */
diff --git a/tools/include/vdso/const.h b/tools/include/vdso/const.h
new file mode 100644
index 000000000000..94b385ad438d
--- /dev/null
+++ b/tools/include/vdso/const.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __VDSO_CONST_H
+#define __VDSO_CONST_H
+
+#include <uapi/linux/const.h>
+
+#define UL(x)		(_UL(x))
+#define ULL(x)		(_ULL(x))
+
+#endif /* __VDSO_CONST_H */
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 44d510bc9b78..37b844f839bc 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -8,357 +8,357 @@
 #
 # The abi is "common", "64" or "x32" for this file.
 #
-0	common	read			__x64_sys_read
-1	common	write			__x64_sys_write
-2	common	open			__x64_sys_open
-3	common	close			__x64_sys_close
-4	common	stat			__x64_sys_newstat
-5	common	fstat			__x64_sys_newfstat
-6	common	lstat			__x64_sys_newlstat
-7	common	poll			__x64_sys_poll
-8	common	lseek			__x64_sys_lseek
-9	common	mmap			__x64_sys_mmap
-10	common	mprotect		__x64_sys_mprotect
-11	common	munmap			__x64_sys_munmap
-12	common	brk			__x64_sys_brk
-13	64	rt_sigaction		__x64_sys_rt_sigaction
-14	common	rt_sigprocmask		__x64_sys_rt_sigprocmask
-15	64	rt_sigreturn		__x64_sys_rt_sigreturn/ptregs
-16	64	ioctl			__x64_sys_ioctl
-17	common	pread64			__x64_sys_pread64
-18	common	pwrite64		__x64_sys_pwrite64
-19	64	readv			__x64_sys_readv
-20	64	writev			__x64_sys_writev
-21	common	access			__x64_sys_access
-22	common	pipe			__x64_sys_pipe
-23	common	select			__x64_sys_select
-24	common	sched_yield		__x64_sys_sched_yield
-25	common	mremap			__x64_sys_mremap
-26	common	msync			__x64_sys_msync
-27	common	mincore			__x64_sys_mincore
-28	common	madvise			__x64_sys_madvise
-29	common	shmget			__x64_sys_shmget
-30	common	shmat			__x64_sys_shmat
-31	common	shmctl			__x64_sys_shmctl
-32	common	dup			__x64_sys_dup
-33	common	dup2			__x64_sys_dup2
-34	common	pause			__x64_sys_pause
-35	common	nanosleep		__x64_sys_nanosleep
-36	common	getitimer		__x64_sys_getitimer
-37	common	alarm			__x64_sys_alarm
-38	common	setitimer		__x64_sys_setitimer
-39	common	getpid			__x64_sys_getpid
-40	common	sendfile		__x64_sys_sendfile64
-41	common	socket			__x64_sys_socket
-42	common	connect			__x64_sys_connect
-43	common	accept			__x64_sys_accept
-44	common	sendto			__x64_sys_sendto
-45	64	recvfrom		__x64_sys_recvfrom
-46	64	sendmsg			__x64_sys_sendmsg
-47	64	recvmsg			__x64_sys_recvmsg
-48	common	shutdown		__x64_sys_shutdown
-49	common	bind			__x64_sys_bind
-50	common	listen			__x64_sys_listen
-51	common	getsockname		__x64_sys_getsockname
-52	common	getpeername		__x64_sys_getpeername
-53	common	socketpair		__x64_sys_socketpair
-54	64	setsockopt		__x64_sys_setsockopt
-55	64	getsockopt		__x64_sys_getsockopt
-56	common	clone			__x64_sys_clone/ptregs
-57	common	fork			__x64_sys_fork/ptregs
-58	common	vfork			__x64_sys_vfork/ptregs
-59	64	execve			__x64_sys_execve/ptregs
-60	common	exit			__x64_sys_exit
-61	common	wait4			__x64_sys_wait4
-62	common	kill			__x64_sys_kill
-63	common	uname			__x64_sys_newuname
-64	common	semget			__x64_sys_semget
-65	common	semop			__x64_sys_semop
-66	common	semctl			__x64_sys_semctl
-67	common	shmdt			__x64_sys_shmdt
-68	common	msgget			__x64_sys_msgget
-69	common	msgsnd			__x64_sys_msgsnd
-70	common	msgrcv			__x64_sys_msgrcv
-71	common	msgctl			__x64_sys_msgctl
-72	common	fcntl			__x64_sys_fcntl
-73	common	flock			__x64_sys_flock
-74	common	fsync			__x64_sys_fsync
-75	common	fdatasync		__x64_sys_fdatasync
-76	common	truncate		__x64_sys_truncate
-77	common	ftruncate		__x64_sys_ftruncate
-78	common	getdents		__x64_sys_getdents
-79	common	getcwd			__x64_sys_getcwd
-80	common	chdir			__x64_sys_chdir
-81	common	fchdir			__x64_sys_fchdir
-82	common	rename			__x64_sys_rename
-83	common	mkdir			__x64_sys_mkdir
-84	common	rmdir			__x64_sys_rmdir
-85	common	creat			__x64_sys_creat
-86	common	link			__x64_sys_link
-87	common	unlink			__x64_sys_unlink
-88	common	symlink			__x64_sys_symlink
-89	common	readlink		__x64_sys_readlink
-90	common	chmod			__x64_sys_chmod
-91	common	fchmod			__x64_sys_fchmod
-92	common	chown			__x64_sys_chown
-93	common	fchown			__x64_sys_fchown
-94	common	lchown			__x64_sys_lchown
-95	common	umask			__x64_sys_umask
-96	common	gettimeofday		__x64_sys_gettimeofday
-97	common	getrlimit		__x64_sys_getrlimit
-98	common	getrusage		__x64_sys_getrusage
-99	common	sysinfo			__x64_sys_sysinfo
-100	common	times			__x64_sys_times
-101	64	ptrace			__x64_sys_ptrace
-102	common	getuid			__x64_sys_getuid
-103	common	syslog			__x64_sys_syslog
-104	common	getgid			__x64_sys_getgid
-105	common	setuid			__x64_sys_setuid
-106	common	setgid			__x64_sys_setgid
-107	common	geteuid			__x64_sys_geteuid
-108	common	getegid			__x64_sys_getegid
-109	common	setpgid			__x64_sys_setpgid
-110	common	getppid			__x64_sys_getppid
-111	common	getpgrp			__x64_sys_getpgrp
-112	common	setsid			__x64_sys_setsid
-113	common	setreuid		__x64_sys_setreuid
-114	common	setregid		__x64_sys_setregid
-115	common	getgroups		__x64_sys_getgroups
-116	common	setgroups		__x64_sys_setgroups
-117	common	setresuid		__x64_sys_setresuid
-118	common	getresuid		__x64_sys_getresuid
-119	common	setresgid		__x64_sys_setresgid
-120	common	getresgid		__x64_sys_getresgid
-121	common	getpgid			__x64_sys_getpgid
-122	common	setfsuid		__x64_sys_setfsuid
-123	common	setfsgid		__x64_sys_setfsgid
-124	common	getsid			__x64_sys_getsid
-125	common	capget			__x64_sys_capget
-126	common	capset			__x64_sys_capset
-127	64	rt_sigpending		__x64_sys_rt_sigpending
-128	64	rt_sigtimedwait		__x64_sys_rt_sigtimedwait
-129	64	rt_sigqueueinfo		__x64_sys_rt_sigqueueinfo
-130	common	rt_sigsuspend		__x64_sys_rt_sigsuspend
-131	64	sigaltstack		__x64_sys_sigaltstack
-132	common	utime			__x64_sys_utime
-133	common	mknod			__x64_sys_mknod
+0	common	read			sys_read
+1	common	write			sys_write
+2	common	open			sys_open
+3	common	close			sys_close
+4	common	stat			sys_newstat
+5	common	fstat			sys_newfstat
+6	common	lstat			sys_newlstat
+7	common	poll			sys_poll
+8	common	lseek			sys_lseek
+9	common	mmap			sys_mmap
+10	common	mprotect		sys_mprotect
+11	common	munmap			sys_munmap
+12	common	brk			sys_brk
+13	64	rt_sigaction		sys_rt_sigaction
+14	common	rt_sigprocmask		sys_rt_sigprocmask
+15	64	rt_sigreturn		sys_rt_sigreturn
+16	64	ioctl			sys_ioctl
+17	common	pread64			sys_pread64
+18	common	pwrite64		sys_pwrite64
+19	64	readv			sys_readv
+20	64	writev			sys_writev
+21	common	access			sys_access
+22	common	pipe			sys_pipe
+23	common	select			sys_select
+24	common	sched_yield		sys_sched_yield
+25	common	mremap			sys_mremap
+26	common	msync			sys_msync
+27	common	mincore			sys_mincore
+28	common	madvise			sys_madvise
+29	common	shmget			sys_shmget
+30	common	shmat			sys_shmat
+31	common	shmctl			sys_shmctl
+32	common	dup			sys_dup
+33	common	dup2			sys_dup2
+34	common	pause			sys_pause
+35	common	nanosleep		sys_nanosleep
+36	common	getitimer		sys_getitimer
+37	common	alarm			sys_alarm
+38	common	setitimer		sys_setitimer
+39	common	getpid			sys_getpid
+40	common	sendfile		sys_sendfile64
+41	common	socket			sys_socket
+42	common	connect			sys_connect
+43	common	accept			sys_accept
+44	common	sendto			sys_sendto
+45	64	recvfrom		sys_recvfrom
+46	64	sendmsg			sys_sendmsg
+47	64	recvmsg			sys_recvmsg
+48	common	shutdown		sys_shutdown
+49	common	bind			sys_bind
+50	common	listen			sys_listen
+51	common	getsockname		sys_getsockname
+52	common	getpeername		sys_getpeername
+53	common	socketpair		sys_socketpair
+54	64	setsockopt		sys_setsockopt
+55	64	getsockopt		sys_getsockopt
+56	common	clone			sys_clone
+57	common	fork			sys_fork
+58	common	vfork			sys_vfork
+59	64	execve			sys_execve
+60	common	exit			sys_exit
+61	common	wait4			sys_wait4
+62	common	kill			sys_kill
+63	common	uname			sys_newuname
+64	common	semget			sys_semget
+65	common	semop			sys_semop
+66	common	semctl			sys_semctl
+67	common	shmdt			sys_shmdt
+68	common	msgget			sys_msgget
+69	common	msgsnd			sys_msgsnd
+70	common	msgrcv			sys_msgrcv
+71	common	msgctl			sys_msgctl
+72	common	fcntl			sys_fcntl
+73	common	flock			sys_flock
+74	common	fsync			sys_fsync
+75	common	fdatasync		sys_fdatasync
+76	common	truncate		sys_truncate
+77	common	ftruncate		sys_ftruncate
+78	common	getdents		sys_getdents
+79	common	getcwd			sys_getcwd
+80	common	chdir			sys_chdir
+81	common	fchdir			sys_fchdir
+82	common	rename			sys_rename
+83	common	mkdir			sys_mkdir
+84	common	rmdir			sys_rmdir
+85	common	creat			sys_creat
+86	common	link			sys_link
+87	common	unlink			sys_unlink
+88	common	symlink			sys_symlink
+89	common	readlink		sys_readlink
+90	common	chmod			sys_chmod
+91	common	fchmod			sys_fchmod
+92	common	chown			sys_chown
+93	common	fchown			sys_fchown
+94	common	lchown			sys_lchown
+95	common	umask			sys_umask
+96	common	gettimeofday		sys_gettimeofday
+97	common	getrlimit		sys_getrlimit
+98	common	getrusage		sys_getrusage
+99	common	sysinfo			sys_sysinfo
+100	common	times			sys_times
+101	64	ptrace			sys_ptrace
+102	common	getuid			sys_getuid
+103	common	syslog			sys_syslog
+104	common	getgid			sys_getgid
+105	common	setuid			sys_setuid
+106	common	setgid			sys_setgid
+107	common	geteuid			sys_geteuid
+108	common	getegid			sys_getegid
+109	common	setpgid			sys_setpgid
+110	common	getppid			sys_getppid
+111	common	getpgrp			sys_getpgrp
+112	common	setsid			sys_setsid
+113	common	setreuid		sys_setreuid
+114	common	setregid		sys_setregid
+115	common	getgroups		sys_getgroups
+116	common	setgroups		sys_setgroups
+117	common	setresuid		sys_setresuid
+118	common	getresuid		sys_getresuid
+119	common	setresgid		sys_setresgid
+120	common	getresgid		sys_getresgid
+121	common	getpgid			sys_getpgid
+122	common	setfsuid		sys_setfsuid
+123	common	setfsgid		sys_setfsgid
+124	common	getsid			sys_getsid
+125	common	capget			sys_capget
+126	common	capset			sys_capset
+127	64	rt_sigpending		sys_rt_sigpending
+128	64	rt_sigtimedwait		sys_rt_sigtimedwait
+129	64	rt_sigqueueinfo		sys_rt_sigqueueinfo
+130	common	rt_sigsuspend		sys_rt_sigsuspend
+131	64	sigaltstack		sys_sigaltstack
+132	common	utime			sys_utime
+133	common	mknod			sys_mknod
 134	64	uselib
-135	common	personality		__x64_sys_personality
-136	common	ustat			__x64_sys_ustat
-137	common	statfs			__x64_sys_statfs
-138	common	fstatfs			__x64_sys_fstatfs
-139	common	sysfs			__x64_sys_sysfs
-140	common	getpriority		__x64_sys_getpriority
-141	common	setpriority		__x64_sys_setpriority
-142	common	sched_setparam		__x64_sys_sched_setparam
-143	common	sched_getparam		__x64_sys_sched_getparam
-144	common	sched_setscheduler	__x64_sys_sched_setscheduler
-145	common	sched_getscheduler	__x64_sys_sched_getscheduler
-146	common	sched_get_priority_max	__x64_sys_sched_get_priority_max
-147	common	sched_get_priority_min	__x64_sys_sched_get_priority_min
-148	common	sched_rr_get_interval	__x64_sys_sched_rr_get_interval
-149	common	mlock			__x64_sys_mlock
-150	common	munlock			__x64_sys_munlock
-151	common	mlockall		__x64_sys_mlockall
-152	common	munlockall		__x64_sys_munlockall
-153	common	vhangup			__x64_sys_vhangup
-154	common	modify_ldt		__x64_sys_modify_ldt
-155	common	pivot_root		__x64_sys_pivot_root
-156	64	_sysctl			__x64_sys_sysctl
-157	common	prctl			__x64_sys_prctl
-158	common	arch_prctl		__x64_sys_arch_prctl
-159	common	adjtimex		__x64_sys_adjtimex
-160	common	setrlimit		__x64_sys_setrlimit
-161	common	chroot			__x64_sys_chroot
-162	common	sync			__x64_sys_sync
-163	common	acct			__x64_sys_acct
-164	common	settimeofday		__x64_sys_settimeofday
-165	common	mount			__x64_sys_mount
-166	common	umount2			__x64_sys_umount
-167	common	swapon			__x64_sys_swapon
-168	common	swapoff			__x64_sys_swapoff
-169	common	reboot			__x64_sys_reboot
-170	common	sethostname		__x64_sys_sethostname
-171	common	setdomainname		__x64_sys_setdomainname
-172	common	iopl			__x64_sys_iopl/ptregs
-173	common	ioperm			__x64_sys_ioperm
+135	common	personality		sys_personality
+136	common	ustat			sys_ustat
+137	common	statfs			sys_statfs
+138	common	fstatfs			sys_fstatfs
+139	common	sysfs			sys_sysfs
+140	common	getpriority		sys_getpriority
+141	common	setpriority		sys_setpriority
+142	common	sched_setparam		sys_sched_setparam
+143	common	sched_getparam		sys_sched_getparam
+144	common	sched_setscheduler	sys_sched_setscheduler
+145	common	sched_getscheduler	sys_sched_getscheduler
+146	common	sched_get_priority_max	sys_sched_get_priority_max
+147	common	sched_get_priority_min	sys_sched_get_priority_min
+148	common	sched_rr_get_interval	sys_sched_rr_get_interval
+149	common	mlock			sys_mlock
+150	common	munlock			sys_munlock
+151	common	mlockall		sys_mlockall
+152	common	munlockall		sys_munlockall
+153	common	vhangup			sys_vhangup
+154	common	modify_ldt		sys_modify_ldt
+155	common	pivot_root		sys_pivot_root
+156	64	_sysctl			sys_sysctl
+157	common	prctl			sys_prctl
+158	common	arch_prctl		sys_arch_prctl
+159	common	adjtimex		sys_adjtimex
+160	common	setrlimit		sys_setrlimit
+161	common	chroot			sys_chroot
+162	common	sync			sys_sync
+163	common	acct			sys_acct
+164	common	settimeofday		sys_settimeofday
+165	common	mount			sys_mount
+166	common	umount2			sys_umount
+167	common	swapon			sys_swapon
+168	common	swapoff			sys_swapoff
+169	common	reboot			sys_reboot
+170	common	sethostname		sys_sethostname
+171	common	setdomainname		sys_setdomainname
+172	common	iopl			sys_iopl
+173	common	ioperm			sys_ioperm
 174	64	create_module
-175	common	init_module		__x64_sys_init_module
-176	common	delete_module		__x64_sys_delete_module
+175	common	init_module		sys_init_module
+176	common	delete_module		sys_delete_module
 177	64	get_kernel_syms
 178	64	query_module
-179	common	quotactl		__x64_sys_quotactl
+179	common	quotactl		sys_quotactl
 180	64	nfsservctl
 181	common	getpmsg
 182	common	putpmsg
 183	common	afs_syscall
 184	common	tuxcall
 185	common	security
-186	common	gettid			__x64_sys_gettid
-187	common	readahead		__x64_sys_readahead
-188	common	setxattr		__x64_sys_setxattr
-189	common	lsetxattr		__x64_sys_lsetxattr
-190	common	fsetxattr		__x64_sys_fsetxattr
-191	common	getxattr		__x64_sys_getxattr
-192	common	lgetxattr		__x64_sys_lgetxattr
-193	common	fgetxattr		__x64_sys_fgetxattr
-194	common	listxattr		__x64_sys_listxattr
-195	common	llistxattr		__x64_sys_llistxattr
-196	common	flistxattr		__x64_sys_flistxattr
-197	common	removexattr		__x64_sys_removexattr
-198	common	lremovexattr		__x64_sys_lremovexattr
-199	common	fremovexattr		__x64_sys_fremovexattr
-200	common	tkill			__x64_sys_tkill
-201	common	time			__x64_sys_time
-202	common	futex			__x64_sys_futex
-203	common	sched_setaffinity	__x64_sys_sched_setaffinity
-204	common	sched_getaffinity	__x64_sys_sched_getaffinity
+186	common	gettid			sys_gettid
+187	common	readahead		sys_readahead
+188	common	setxattr		sys_setxattr
+189	common	lsetxattr		sys_lsetxattr
+190	common	fsetxattr		sys_fsetxattr
+191	common	getxattr		sys_getxattr
+192	common	lgetxattr		sys_lgetxattr
+193	common	fgetxattr		sys_fgetxattr
+194	common	listxattr		sys_listxattr
+195	common	llistxattr		sys_llistxattr
+196	common	flistxattr		sys_flistxattr
+197	common	removexattr		sys_removexattr
+198	common	lremovexattr		sys_lremovexattr
+199	common	fremovexattr		sys_fremovexattr
+200	common	tkill			sys_tkill
+201	common	time			sys_time
+202	common	futex			sys_futex
+203	common	sched_setaffinity	sys_sched_setaffinity
+204	common	sched_getaffinity	sys_sched_getaffinity
 205	64	set_thread_area
-206	64	io_setup		__x64_sys_io_setup
-207	common	io_destroy		__x64_sys_io_destroy
-208	common	io_getevents		__x64_sys_io_getevents
-209	64	io_submit		__x64_sys_io_submit
-210	common	io_cancel		__x64_sys_io_cancel
+206	64	io_setup		sys_io_setup
+207	common	io_destroy		sys_io_destroy
+208	common	io_getevents		sys_io_getevents
+209	64	io_submit		sys_io_submit
+210	common	io_cancel		sys_io_cancel
 211	64	get_thread_area
-212	common	lookup_dcookie		__x64_sys_lookup_dcookie
-213	common	epoll_create		__x64_sys_epoll_create
+212	common	lookup_dcookie		sys_lookup_dcookie
+213	common	epoll_create		sys_epoll_create
 214	64	epoll_ctl_old
 215	64	epoll_wait_old
-216	common	remap_file_pages	__x64_sys_remap_file_pages
-217	common	getdents64		__x64_sys_getdents64
-218	common	set_tid_address		__x64_sys_set_tid_address
-219	common	restart_syscall		__x64_sys_restart_syscall
-220	common	semtimedop		__x64_sys_semtimedop
-221	common	fadvise64		__x64_sys_fadvise64
-222	64	timer_create		__x64_sys_timer_create
-223	common	timer_settime		__x64_sys_timer_settime
-224	common	timer_gettime		__x64_sys_timer_gettime
-225	common	timer_getoverrun	__x64_sys_timer_getoverrun
-226	common	timer_delete		__x64_sys_timer_delete
-227	common	clock_settime		__x64_sys_clock_settime
-228	common	clock_gettime		__x64_sys_clock_gettime
-229	common	clock_getres		__x64_sys_clock_getres
-230	common	clock_nanosleep		__x64_sys_clock_nanosleep
-231	common	exit_group		__x64_sys_exit_group
-232	common	epoll_wait		__x64_sys_epoll_wait
-233	common	epoll_ctl		__x64_sys_epoll_ctl
-234	common	tgkill			__x64_sys_tgkill
-235	common	utimes			__x64_sys_utimes
+216	common	remap_file_pages	sys_remap_file_pages
+217	common	getdents64		sys_getdents64
+218	common	set_tid_address		sys_set_tid_address
+219	common	restart_syscall		sys_restart_syscall
+220	common	semtimedop		sys_semtimedop
+221	common	fadvise64		sys_fadvise64
+222	64	timer_create		sys_timer_create
+223	common	timer_settime		sys_timer_settime
+224	common	timer_gettime		sys_timer_gettime
+225	common	timer_getoverrun	sys_timer_getoverrun
+226	common	timer_delete		sys_timer_delete
+227	common	clock_settime		sys_clock_settime
+228	common	clock_gettime		sys_clock_gettime
+229	common	clock_getres		sys_clock_getres
+230	common	clock_nanosleep		sys_clock_nanosleep
+231	common	exit_group		sys_exit_group
+232	common	epoll_wait		sys_epoll_wait
+233	common	epoll_ctl		sys_epoll_ctl
+234	common	tgkill			sys_tgkill
+235	common	utimes			sys_utimes
 236	64	vserver
-237	common	mbind			__x64_sys_mbind
-238	common	set_mempolicy		__x64_sys_set_mempolicy
-239	common	get_mempolicy		__x64_sys_get_mempolicy
-240	common	mq_open			__x64_sys_mq_open
-241	common	mq_unlink		__x64_sys_mq_unlink
-242	common	mq_timedsend		__x64_sys_mq_timedsend
-243	common	mq_timedreceive		__x64_sys_mq_timedreceive
-244	64	mq_notify		__x64_sys_mq_notify
-245	common	mq_getsetattr		__x64_sys_mq_getsetattr
-246	64	kexec_load		__x64_sys_kexec_load
-247	64	waitid			__x64_sys_waitid
-248	common	add_key			__x64_sys_add_key
-249	common	request_key		__x64_sys_request_key
-250	common	keyctl			__x64_sys_keyctl
-251	common	ioprio_set		__x64_sys_ioprio_set
-252	common	ioprio_get		__x64_sys_ioprio_get
-253	common	inotify_init		__x64_sys_inotify_init
-254	common	inotify_add_watch	__x64_sys_inotify_add_watch
-255	common	inotify_rm_watch	__x64_sys_inotify_rm_watch
-256	common	migrate_pages		__x64_sys_migrate_pages
-257	common	openat			__x64_sys_openat
-258	common	mkdirat			__x64_sys_mkdirat
-259	common	mknodat			__x64_sys_mknodat
-260	common	fchownat		__x64_sys_fchownat
-261	common	futimesat		__x64_sys_futimesat
-262	common	newfstatat		__x64_sys_newfstatat
-263	common	unlinkat		__x64_sys_unlinkat
-264	common	renameat		__x64_sys_renameat
-265	common	linkat			__x64_sys_linkat
-266	common	symlinkat		__x64_sys_symlinkat
-267	common	readlinkat		__x64_sys_readlinkat
-268	common	fchmodat		__x64_sys_fchmodat
-269	common	faccessat		__x64_sys_faccessat
-270	common	pselect6		__x64_sys_pselect6
-271	common	ppoll			__x64_sys_ppoll
-272	common	unshare			__x64_sys_unshare
-273	64	set_robust_list		__x64_sys_set_robust_list
-274	64	get_robust_list		__x64_sys_get_robust_list
-275	common	splice			__x64_sys_splice
-276	common	tee			__x64_sys_tee
-277	common	sync_file_range		__x64_sys_sync_file_range
-278	64	vmsplice		__x64_sys_vmsplice
-279	64	move_pages		__x64_sys_move_pages
-280	common	utimensat		__x64_sys_utimensat
-281	common	epoll_pwait		__x64_sys_epoll_pwait
-282	common	signalfd		__x64_sys_signalfd
-283	common	timerfd_create		__x64_sys_timerfd_create
-284	common	eventfd			__x64_sys_eventfd
-285	common	fallocate		__x64_sys_fallocate
-286	common	timerfd_settime		__x64_sys_timerfd_settime
-287	common	timerfd_gettime		__x64_sys_timerfd_gettime
-288	common	accept4			__x64_sys_accept4
-289	common	signalfd4		__x64_sys_signalfd4
-290	common	eventfd2		__x64_sys_eventfd2
-291	common	epoll_create1		__x64_sys_epoll_create1
-292	common	dup3			__x64_sys_dup3
-293	common	pipe2			__x64_sys_pipe2
-294	common	inotify_init1		__x64_sys_inotify_init1
-295	64	preadv			__x64_sys_preadv
-296	64	pwritev			__x64_sys_pwritev
-297	64	rt_tgsigqueueinfo	__x64_sys_rt_tgsigqueueinfo
-298	common	perf_event_open		__x64_sys_perf_event_open
-299	64	recvmmsg		__x64_sys_recvmmsg
-300	common	fanotify_init		__x64_sys_fanotify_init
-301	common	fanotify_mark		__x64_sys_fanotify_mark
-302	common	prlimit64		__x64_sys_prlimit64
-303	common	name_to_handle_at	__x64_sys_name_to_handle_at
-304	common	open_by_handle_at	__x64_sys_open_by_handle_at
-305	common	clock_adjtime		__x64_sys_clock_adjtime
-306	common	syncfs			__x64_sys_syncfs
-307	64	sendmmsg		__x64_sys_sendmmsg
-308	common	setns			__x64_sys_setns
-309	common	getcpu			__x64_sys_getcpu
-310	64	process_vm_readv	__x64_sys_process_vm_readv
-311	64	process_vm_writev	__x64_sys_process_vm_writev
-312	common	kcmp			__x64_sys_kcmp
-313	common	finit_module		__x64_sys_finit_module
-314	common	sched_setattr		__x64_sys_sched_setattr
-315	common	sched_getattr		__x64_sys_sched_getattr
-316	common	renameat2		__x64_sys_renameat2
-317	common	seccomp			__x64_sys_seccomp
-318	common	getrandom		__x64_sys_getrandom
-319	common	memfd_create		__x64_sys_memfd_create
-320	common	kexec_file_load		__x64_sys_kexec_file_load
-321	common	bpf			__x64_sys_bpf
-322	64	execveat		__x64_sys_execveat/ptregs
-323	common	userfaultfd		__x64_sys_userfaultfd
-324	common	membarrier		__x64_sys_membarrier
-325	common	mlock2			__x64_sys_mlock2
-326	common	copy_file_range		__x64_sys_copy_file_range
-327	64	preadv2			__x64_sys_preadv2
-328	64	pwritev2		__x64_sys_pwritev2
-329	common	pkey_mprotect		__x64_sys_pkey_mprotect
-330	common	pkey_alloc		__x64_sys_pkey_alloc
-331	common	pkey_free		__x64_sys_pkey_free
-332	common	statx			__x64_sys_statx
-333	common	io_pgetevents		__x64_sys_io_pgetevents
-334	common	rseq			__x64_sys_rseq
+237	common	mbind			sys_mbind
+238	common	set_mempolicy		sys_set_mempolicy
+239	common	get_mempolicy		sys_get_mempolicy
+240	common	mq_open			sys_mq_open
+241	common	mq_unlink		sys_mq_unlink
+242	common	mq_timedsend		sys_mq_timedsend
+243	common	mq_timedreceive		sys_mq_timedreceive
+244	64	mq_notify		sys_mq_notify
+245	common	mq_getsetattr		sys_mq_getsetattr
+246	64	kexec_load		sys_kexec_load
+247	64	waitid			sys_waitid
+248	common	add_key			sys_add_key
+249	common	request_key		sys_request_key
+250	common	keyctl			sys_keyctl
+251	common	ioprio_set		sys_ioprio_set
+252	common	ioprio_get		sys_ioprio_get
+253	common	inotify_init		sys_inotify_init
+254	common	inotify_add_watch	sys_inotify_add_watch
+255	common	inotify_rm_watch	sys_inotify_rm_watch
+256	common	migrate_pages		sys_migrate_pages
+257	common	openat			sys_openat
+258	common	mkdirat			sys_mkdirat
+259	common	mknodat			sys_mknodat
+260	common	fchownat		sys_fchownat
+261	common	futimesat		sys_futimesat
+262	common	newfstatat		sys_newfstatat
+263	common	unlinkat		sys_unlinkat
+264	common	renameat		sys_renameat
+265	common	linkat			sys_linkat
+266	common	symlinkat		sys_symlinkat
+267	common	readlinkat		sys_readlinkat
+268	common	fchmodat		sys_fchmodat
+269	common	faccessat		sys_faccessat
+270	common	pselect6		sys_pselect6
+271	common	ppoll			sys_ppoll
+272	common	unshare			sys_unshare
+273	64	set_robust_list		sys_set_robust_list
+274	64	get_robust_list		sys_get_robust_list
+275	common	splice			sys_splice
+276	common	tee			sys_tee
+277	common	sync_file_range		sys_sync_file_range
+278	64	vmsplice		sys_vmsplice
+279	64	move_pages		sys_move_pages
+280	common	utimensat		sys_utimensat
+281	common	epoll_pwait		sys_epoll_pwait
+282	common	signalfd		sys_signalfd
+283	common	timerfd_create		sys_timerfd_create
+284	common	eventfd			sys_eventfd
+285	common	fallocate		sys_fallocate
+286	common	timerfd_settime		sys_timerfd_settime
+287	common	timerfd_gettime		sys_timerfd_gettime
+288	common	accept4			sys_accept4
+289	common	signalfd4		sys_signalfd4
+290	common	eventfd2		sys_eventfd2
+291	common	epoll_create1		sys_epoll_create1
+292	common	dup3			sys_dup3
+293	common	pipe2			sys_pipe2
+294	common	inotify_init1		sys_inotify_init1
+295	64	preadv			sys_preadv
+296	64	pwritev			sys_pwritev
+297	64	rt_tgsigqueueinfo	sys_rt_tgsigqueueinfo
+298	common	perf_event_open		sys_perf_event_open
+299	64	recvmmsg		sys_recvmmsg
+300	common	fanotify_init		sys_fanotify_init
+301	common	fanotify_mark		sys_fanotify_mark
+302	common	prlimit64		sys_prlimit64
+303	common	name_to_handle_at	sys_name_to_handle_at
+304	common	open_by_handle_at	sys_open_by_handle_at
+305	common	clock_adjtime		sys_clock_adjtime
+306	common	syncfs			sys_syncfs
+307	64	sendmmsg		sys_sendmmsg
+308	common	setns			sys_setns
+309	common	getcpu			sys_getcpu
+310	64	process_vm_readv	sys_process_vm_readv
+311	64	process_vm_writev	sys_process_vm_writev
+312	common	kcmp			sys_kcmp
+313	common	finit_module		sys_finit_module
+314	common	sched_setattr		sys_sched_setattr
+315	common	sched_getattr		sys_sched_getattr
+316	common	renameat2		sys_renameat2
+317	common	seccomp			sys_seccomp
+318	common	getrandom		sys_getrandom
+319	common	memfd_create		sys_memfd_create
+320	common	kexec_file_load		sys_kexec_file_load
+321	common	bpf			sys_bpf
+322	64	execveat		sys_execveat
+323	common	userfaultfd		sys_userfaultfd
+324	common	membarrier		sys_membarrier
+325	common	mlock2			sys_mlock2
+326	common	copy_file_range		sys_copy_file_range
+327	64	preadv2			sys_preadv2
+328	64	pwritev2		sys_pwritev2
+329	common	pkey_mprotect		sys_pkey_mprotect
+330	common	pkey_alloc		sys_pkey_alloc
+331	common	pkey_free		sys_pkey_free
+332	common	statx			sys_statx
+333	common	io_pgetevents		sys_io_pgetevents
+334	common	rseq			sys_rseq
 # don't use numbers 387 through 423, add new calls after the last
 # 'common' entry
-424	common	pidfd_send_signal	__x64_sys_pidfd_send_signal
-425	common	io_uring_setup		__x64_sys_io_uring_setup
-426	common	io_uring_enter		__x64_sys_io_uring_enter
-427	common	io_uring_register	__x64_sys_io_uring_register
-428	common	open_tree		__x64_sys_open_tree
-429	common	move_mount		__x64_sys_move_mount
-430	common	fsopen			__x64_sys_fsopen
-431	common	fsconfig		__x64_sys_fsconfig
-432	common	fsmount			__x64_sys_fsmount
-433	common	fspick			__x64_sys_fspick
-434	common	pidfd_open		__x64_sys_pidfd_open
-435	common	clone3			__x64_sys_clone3/ptregs
-437	common	openat2			__x64_sys_openat2
-438	common	pidfd_getfd		__x64_sys_pidfd_getfd
+424	common	pidfd_send_signal	sys_pidfd_send_signal
+425	common	io_uring_setup		sys_io_uring_setup
+426	common	io_uring_enter		sys_io_uring_enter
+427	common	io_uring_register	sys_io_uring_register
+428	common	open_tree		sys_open_tree
+429	common	move_mount		sys_move_mount
+430	common	fsopen			sys_fsopen
+431	common	fsconfig		sys_fsconfig
+432	common	fsmount			sys_fsmount
+433	common	fspick			sys_fspick
+434	common	pidfd_open		sys_pidfd_open
+435	common	clone3			sys_clone3
+437	common	openat2			sys_openat2
+438	common	pidfd_getfd		sys_pidfd_getfd
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
@@ -366,39 +366,39 @@
 # on-the-fly for compat_sys_*() compatibility system calls if X86_X32
 # is defined.
 #
-512	x32	rt_sigaction		__x32_compat_sys_rt_sigaction
-513	x32	rt_sigreturn		sys32_x32_rt_sigreturn
-514	x32	ioctl			__x32_compat_sys_ioctl
-515	x32	readv			__x32_compat_sys_readv
-516	x32	writev			__x32_compat_sys_writev
-517	x32	recvfrom		__x32_compat_sys_recvfrom
-518	x32	sendmsg			__x32_compat_sys_sendmsg
-519	x32	recvmsg			__x32_compat_sys_recvmsg
-520	x32	execve			__x32_compat_sys_execve/ptregs
-521	x32	ptrace			__x32_compat_sys_ptrace
-522	x32	rt_sigpending		__x32_compat_sys_rt_sigpending
-523	x32	rt_sigtimedwait		__x32_compat_sys_rt_sigtimedwait_time64
-524	x32	rt_sigqueueinfo		__x32_compat_sys_rt_sigqueueinfo
-525	x32	sigaltstack		__x32_compat_sys_sigaltstack
-526	x32	timer_create		__x32_compat_sys_timer_create
-527	x32	mq_notify		__x32_compat_sys_mq_notify
-528	x32	kexec_load		__x32_compat_sys_kexec_load
-529	x32	waitid			__x32_compat_sys_waitid
-530	x32	set_robust_list		__x32_compat_sys_set_robust_list
-531	x32	get_robust_list		__x32_compat_sys_get_robust_list
-532	x32	vmsplice		__x32_compat_sys_vmsplice
-533	x32	move_pages		__x32_compat_sys_move_pages
-534	x32	preadv			__x32_compat_sys_preadv64
-535	x32	pwritev			__x32_compat_sys_pwritev64
-536	x32	rt_tgsigqueueinfo	__x32_compat_sys_rt_tgsigqueueinfo
-537	x32	recvmmsg		__x32_compat_sys_recvmmsg_time64
-538	x32	sendmmsg		__x32_compat_sys_sendmmsg
-539	x32	process_vm_readv	__x32_compat_sys_process_vm_readv
-540	x32	process_vm_writev	__x32_compat_sys_process_vm_writev
-541	x32	setsockopt		__x32_compat_sys_setsockopt
-542	x32	getsockopt		__x32_compat_sys_getsockopt
-543	x32	io_setup		__x32_compat_sys_io_setup
-544	x32	io_submit		__x32_compat_sys_io_submit
-545	x32	execveat		__x32_compat_sys_execveat/ptregs
-546	x32	preadv2			__x32_compat_sys_preadv64v2
-547	x32	pwritev2		__x32_compat_sys_pwritev64v2
+512	x32	rt_sigaction		compat_sys_rt_sigaction
+513	x32	rt_sigreturn		compat_sys_x32_rt_sigreturn
+514	x32	ioctl			compat_sys_ioctl
+515	x32	readv			compat_sys_readv
+516	x32	writev			compat_sys_writev
+517	x32	recvfrom		compat_sys_recvfrom
+518	x32	sendmsg			compat_sys_sendmsg
+519	x32	recvmsg			compat_sys_recvmsg
+520	x32	execve			compat_sys_execve
+521	x32	ptrace			compat_sys_ptrace
+522	x32	rt_sigpending		compat_sys_rt_sigpending
+523	x32	rt_sigtimedwait		compat_sys_rt_sigtimedwait_time64
+524	x32	rt_sigqueueinfo		compat_sys_rt_sigqueueinfo
+525	x32	sigaltstack		compat_sys_sigaltstack
+526	x32	timer_create		compat_sys_timer_create
+527	x32	mq_notify		compat_sys_mq_notify
+528	x32	kexec_load		compat_sys_kexec_load
+529	x32	waitid			compat_sys_waitid
+530	x32	set_robust_list		compat_sys_set_robust_list
+531	x32	get_robust_list		compat_sys_get_robust_list
+532	x32	vmsplice		compat_sys_vmsplice
+533	x32	move_pages		compat_sys_move_pages
+534	x32	preadv			compat_sys_preadv64
+535	x32	pwritev			compat_sys_pwritev64
+536	x32	rt_tgsigqueueinfo	compat_sys_rt_tgsigqueueinfo
+537	x32	recvmmsg		compat_sys_recvmmsg_time64
+538	x32	sendmmsg		compat_sys_sendmmsg
+539	x32	process_vm_readv	compat_sys_process_vm_readv
+540	x32	process_vm_writev	compat_sys_process_vm_writev
+541	x32	setsockopt		compat_sys_setsockopt
+542	x32	getsockopt		compat_sys_getsockopt
+543	x32	io_setup		compat_sys_io_setup
+544	x32	io_submit		compat_sys_io_submit
+545	x32	execveat		compat_sys_execveat
+546	x32	preadv2			compat_sys_preadv64v2
+547	x32	pwritev2		compat_sys_pwritev64v2
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index bfb21d049e6c..cf147db4e5ca 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -22,7 +22,9 @@ include/uapi/linux/usbdevice_fs.h
 include/uapi/linux/vhost.h
 include/uapi/sound/asound.h
 include/linux/bits.h
+include/vdso/bits.h
 include/linux/const.h
+include/vdso/const.h
 include/linux/hash.h
 include/uapi/linux/hw_breakpoint.h
 arch/x86/include/asm/disabled-features.h
@@ -115,6 +117,7 @@ check arch/x86/lib/memcpy_64.S        '-I "^EXPORT_SYMBOL" -I "^#include <asm/ex
 check arch/x86/lib/memset_64.S        '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memset_\(erms\|orig\))"'
 check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common\(-tools\)*.h>"'
 check include/uapi/linux/mman.h       '-I "^#include <\(uapi/\)*asm/mman.h>"'
+check include/linux/build_bug.h       '-I "^#\(ifndef\|endif\)\( \/\/\)* static_assert$"'
 check include/linux/ctype.h	      '-I "isdigit("'
 check lib/ctype.c		      '-I "^EXPORT_SYMBOL" -I "^#include <linux/export.h>" -B'
 check arch/x86/include/asm/inat.h     '-I "^#include [\"<]\(asm/\)*inat_types.h[\">]"'
diff --git a/tools/perf/trace/beauty/clone.c b/tools/perf/trace/beauty/clone.c
index 062ca849c8fd..f4db894e0af6 100644
--- a/tools/perf/trace/beauty/clone.c
+++ b/tools/perf/trace/beauty/clone.c
@@ -46,6 +46,7 @@ static size_t clone__scnprintf_flags(unsigned long flags, char *bf, size_t size,
 	P_FLAG(NEWNET);
 	P_FLAG(IO);
 	P_FLAG(CLEAR_SIGHAND);
+	P_FLAG(INTO_CGROUP);
 #undef P_FLAG
 
 	if (flags)
diff --git a/tools/perf/trace/beauty/mmap.c b/tools/perf/trace/beauty/mmap.c
index 9fa771a90d79..862c8331dded 100644
--- a/tools/perf/trace/beauty/mmap.c
+++ b/tools/perf/trace/beauty/mmap.c
@@ -69,6 +69,7 @@ static size_t syscall_arg__scnprintf_mremap_flags(char *bf, size_t size,
 
 	P_MREMAP_FLAG(MAYMOVE);
 	P_MREMAP_FLAG(FIXED);
+	P_MREMAP_FLAG(DONTUNMAP);
 #undef P_MREMAP_FLAG
 
 	if (flags)
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 347b2c0789e4..c5e3e9a68162 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -21,6 +21,8 @@ if cc_is_clang:
             vars[var] = sub("-fstack-clash-protection", "", vars[var])
         if not clang_has_option("-fstack-protector-strong"):
             vars[var] = sub("-fstack-protector-strong", "", vars[var])
+        if not clang_has_option("-fno-semantic-interposition"):
+            vars[var] = sub("-fno-semantic-interposition", "", vars[var])
 
 from distutils.core import setup, Extension
 
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 0fd713d3674f..03ecb8cd0eec 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -803,8 +803,11 @@ static void generic_metric(struct perf_stat_config *config,
 				     out->force_header ?
 				     (metric_name ? metric_name : name) : "", 0);
 		}
-	} else
-		print_metric(config, ctxp, NULL, NULL, "", 0);
+	} else {
+		print_metric(config, ctxp, NULL, NULL,
+			     out->force_header ?
+			     (metric_name ? metric_name : name) : "", 0);
+	}
 
 	for (i = 1; i < pctx.num_ids; i++)
 		zfree(&pctx.ids[i].name);

Re: [GIT pull] perf/urgent for 5.7-rc2

[Linus Torvalds]

On Sun, Apr 19, 2020 at 6:57 AM Thomas Gleixner <tglx@linutronix.de> wrote:
>
> please pull the latest perf/urgent branch from:
>
>    git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2020-04-19

So this one took me by surprise, because it only touched the 'tools'
subdirectory for the perf tool, and then when I did what I thought
would be a trivial test build, it re-built the whole kernel.

And that made me go "Whaa?!?"

After looking at it for a while (longer than I really want to admit),
I realized that it's because the headers are also shared with objtool,
and it all kind of made sense.

I say "kind of" because I would have wished that objtool wouldn't
necessarily rebuild everything.

So I'm wondering if there any way that objtool could be run at
link-time (and archive time) rather than force a re-build of all the
object files from source?

This is not a huge deal, it's not like the occasional full rebuild is
_that_ big of a problem, but since I was surprised, I thought I'd
ask..

              Linus

Re: [GIT pull] perf/urgent for 5.7-rc2

[Josh Poimboeuf]

On Sun, Apr 19, 2020 at 11:56:51AM -0700, Linus Torvalds wrote:
> On Sun, Apr 19, 2020 at 6:57 AM Thomas Gleixner <tglx@linutronix.de> wrote:
> >
> > please pull the latest perf/urgent branch from:
> >
> >    git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2020-04-19
> 
> So this one took me by surprise, because it only touched the 'tools'
> subdirectory for the perf tool, and then when I did what I thought
> would be a trivial test build, it re-built the whole kernel.
> 
> And that made me go "Whaa?!?"
> 
> After looking at it for a while (longer than I really want to admit),
> I realized that it's because the headers are also shared with objtool,
> and it all kind of made sense.
> 
> I say "kind of" because I would have wished that objtool wouldn't
> necessarily rebuild everything.

Objtool is run against every .o file, and it's considered part of the
toolchain, because of ORC generation and other reasons.  If anything in
the toolchain changes, everything gets rebuilt.  It *is* kind of crude,
because GCC shouldn't really need to run again.  I don't know if there's
a more refined way to handle that dependency.  ccache helps :-)

> So I'm wondering if there any way that objtool could be run at
> link-time (and archive time) rather than force a re-build of all the
> object files from source?

We've actually been making progress in that direction.  Peter added
partial vmlinux.o support, for Thomas' noinstr validation.  The problem
is, linking is single-threaded so it ends up making the kernel build
slower overall.

So right now, we still do most things per compilation unit, and only do
the noinstr validation at vmlinux.o link time.  Eventually, especially
with LTO, we'll probably end up moving everything over to link time.

-- 
Josh

Re: [GIT pull] perf/urgent for 5.7-rc2

[Ingo Molnar]

* Josh Poimboeuf <jpoimboe@redhat.com> wrote:

> On Sun, Apr 19, 2020 at 11:56:51AM -0700, Linus Torvalds wrote:
> 
> > So I'm wondering if there any way that objtool could be run at 
> > link-time (and archive time) rather than force a re-build of all the 
> > object files from source?
> 
> We've actually been making progress in that direction.  Peter added 
> partial vmlinux.o support, for Thomas' noinstr validation.  The problem 
> is, linking is single-threaded so it ends up making the kernel build 
> slower overall.
> 
> So right now, we still do most things per compilation unit, and only do 
> the noinstr validation at vmlinux.o link time.  Eventually, especially 
> with LTO, we'll probably end up moving everything over to link time.

Fortunately, much of what objtool does against vmlinux.o can be 
parallelized in a rather straightforward fashion I believe, if we build 
with -ffunction-sections.

Here's the main "objtool check" processing steps:

int check(const char *_objname, bool orc)
{
...
        ret = decode_sections(&file);
...

        ret = validate_functions(&file);
...
        ret = validate_unwind_hints(&file);
...
                ret = validate_reachable_instructions(&file);
...
                ret = create_orc(&file);
...
                ret = create_orc_sections(&file);
}

The 'decode_sections()' step takes about 92% of the runtime against 
vmlinux.o:

 $ taskset 1 perf stat --repeat 3 --sync --null tools/objtool/objtool check vmlinux.o

 Performance counter stats for 'tools/objtool/objtool check vmlinux.o' (3 runs):

           3.05757 +- 0.00247 seconds time elapsed  ( +-  0.08% )

 $ taskset 1 perf stat --repeat 3 --exit-after-decode --null tools/objtool/objtool check vmlinux.o            

 Performance counter stats for 'tools/objtool/objtool check vmlinux.o' (3 runs):

           2.83132 +- 0.00272 seconds time elapsed  ( +-  0.10% )

(The --exit-after-decode hack makes it exit right after 
decode_sections().)

Within decode_sections(), the main overhead is in decode_instructions() 
(~75% of the total objtool overhead):

           2.31325 +- 0.00609 seconds time elapsed  ( +-  0.26% )

This goes through every executable section, to decode the instructions:

static int decode_instructions(struct objtool_file *file)
{
...
        for_each_sec(file, sec) {

                if (!(sec->sh.sh_flags & SHF_EXECINSTR))
                        continue;

The size distribution of function section sizes is strongly biased 
towards section sizes of 100 bytes or less, over 95% of all instructions 
in the vmlinux.o are in such a section.

In fact over 99% of all decoded instructions are in a section of 500 
bytes or smaller, so a threaded decoder where each thread batch-decodes a 
handful of sections in a single processing step and then batch-inserts it 
into the (global) instructions hash should do the trick.

The batching size could be driven by section byte size, i.e. we could say 
that the unit of batching is for a decoding thread to grab ~10k bytes 
worth of sections from the list, build a local list of decoded 
instructions, and then insert them into the global hash in a single go. 
This would scale very well IMO, with the defconfig already having almost 
3 million instructions, and a distro build or allmodconfig build a lot 
more.

I believe the 3.0 seconds total objdump runtime above could be reduced to 
below 1.0 second on typical contemporary development systems - which 
would IMHO make it a feasible model to run objtool only against the whole 
kernel binary.

Is there any code generation disadvantage or other quirk to 
-ffunction-sections, or other complications that I missed, that would 
make this difficult?

Thanks,

	Ingo

Re: [GIT pull] perf/urgent for 5.7-rc2

[Peter Zijlstra]

On Mon, Apr 20, 2020 at 09:48:45AM +0200, Ingo Molnar wrote:
> Fortunately, much of what objtool does against vmlinux.o can be 
> parallelized in a rather straightforward fashion I believe, if we build 
> with -ffunction-sections.

So that FGKASLR is going to get us -ffunction-sections, but
parallelizing objtool isn't going to be trivial, it's data structures
aren't really build for that, esp. decode_instructions() which actively
generates data.

Still, it's probably doable.

Re: [GIT pull] perf/urgent for 5.7-rc2

[Ingo Molnar]

* Peter Zijlstra <peterz@infradead.org> wrote:

> On Mon, Apr 20, 2020 at 09:48:45AM +0200, Ingo Molnar wrote:
> > Fortunately, much of what objtool does against vmlinux.o can be 
> > parallelized in a rather straightforward fashion I believe, if we build 
> > with -ffunction-sections.
> 
> So that FGKASLR is going to get us -ffunction-sections, but
> parallelizing objtool isn't going to be trivial, it's data structures
> aren't really build for that, esp. decode_instructions() which actively
> generates data.
> 
> Still, it's probably doable.

So AFAICS in the narrow code section I identified as the main overhead, 
only the instruction hash needs threading, i.e. this step:

                        hash_add(file->insn_hash, &insn->hash, insn->offset);
                        list_add_tail(&insn->list, &file->insn_list);

Objtool can still be single-threaded before and after generating the 
instruction hash.

99% of the overhead within decode_instructions() is in 
arch_decode_instruction(), which is fully thread-safe AFAICS.

So the run time of objtool could be cut in ~third on most systems.

Thanks,

	Ingo

Re: [GIT pull] perf/urgent for 5.7-rc2

[Peter Zijlstra]

On Wed, Apr 22, 2020 at 09:45:12AM +0200, Ingo Molnar wrote:
> 
> * Peter Zijlstra <peterz@infradead.org> wrote:
> 
> > On Mon, Apr 20, 2020 at 09:48:45AM +0200, Ingo Molnar wrote:
> > > Fortunately, much of what objtool does against vmlinux.o can be 
> > > parallelized in a rather straightforward fashion I believe, if we build 
> > > with -ffunction-sections.
> > 
> > So that FGKASLR is going to get us -ffunction-sections, but
> > parallelizing objtool isn't going to be trivial, it's data structures
> > aren't really build for that, esp. decode_instructions() which actively
> > generates data.
> > 
> > Still, it's probably doable.
> 
> So AFAICS in the narrow code section I identified as the main overhead, 
> only the instruction hash needs threading, i.e. this step:
> 
>                         hash_add(file->insn_hash, &insn->hash, insn->offset);
>                         list_add_tail(&insn->list, &file->insn_list);
> 
> Objtool can still be single-threaded before and after generating the 
> instruction hash.
> 
> 99% of the overhead within decode_instructions() is in 
> arch_decode_instruction(), which is fully thread-safe AFAICS.

Correct; I suppose you can farm out the sections to N threads for
arch_decode_instruction() and then have the main thread collect decoded
sections and frob them in the global data structures.

Another pass you can probably parallize fairly easily is
validate_functions() / validate_unwind_hints(). While that modifies
state, the state it modifies should be local to the section at hand.

That needs an audit of course, but it should be entirely doable.

Re: [GIT pull] perf/urgent for 5.7-rc2

[Linus Torvalds]

On Mon, Apr 20, 2020 at 12:48 AM Ingo Molnar <mingo@kernel.org> wrote:
>
> Fortunately, much of what objtool does against vmlinux.o can be
> parallelized in a rather straightforward fashion I believe, if we build
> with -ffunction-sections.

Well, I was actually thinking about a simpler model.

By "link time" I didn't mean "after final link". Yes, there may be
reasons to do it at that point too (to do any whole-program checks),
but that wasn't what I meant.

I meant literally doing it in the $(LD) and $(AR) phases, when you
still have lots of independent object files that you are just about to
link (or archive - do we even do that any more?) into one.

Then you'd parallelize exactly the same way we do now: one object file
at a time, and with no real change of semantics.

IOW, what I was thinking that instead of doing it as part of a final
step after the CC/AS, we'd do it as a preparatory step before the
LD/AR. Same exact operation, same exact target *.o files, just shifted
in time.

             Linus

Re: [GIT pull] perf/urgent for 5.7-rc2

[Peter Zijlstra]

On Mon, Apr 20, 2020 at 09:51:55AM -0700, Linus Torvalds wrote:
> On Mon, Apr 20, 2020 at 12:48 AM Ingo Molnar <mingo@kernel.org> wrote:
> >
> > Fortunately, much of what objtool does against vmlinux.o can be
> > parallelized in a rather straightforward fashion I believe, if we build
> > with -ffunction-sections.
> 
> Well, I was actually thinking about a simpler model.
> 
> By "link time" I didn't mean "after final link". Yes, there may be
> reasons to do it at that point too (to do any whole-program checks),
> but that wasn't what I meant.
> 
> I meant literally doing it in the $(LD) and $(AR) phases, when you
> still have lots of independent object files that you are just about to
> link (or archive - do we even do that any more?) into one.
> 
> Then you'd parallelize exactly the same way we do now: one object file
> at a time, and with no real change of semantics.
> 
> IOW, what I was thinking that instead of doing it as part of a final
> step after the CC/AS, we'd do it as a preparatory step before the
> LD/AR. Same exact operation, same exact target *.o files, just shifted
> in time.

So my pet peeve is that when objtool errors, or crashes, the .o file
gets deleted and it becomes really hard to debug the situation. I'm
thinking that your suggestion would actually help with that too.

I just don't have enough Kbuild foo to even attempt this :/

Re: [GIT pull] perf/urgent for 5.7-rc2

[Josh Poimboeuf]

On Mon, Apr 20, 2020 at 07:40:31PM +0200, Peter Zijlstra wrote:
> On Mon, Apr 20, 2020 at 09:51:55AM -0700, Linus Torvalds wrote:
> > On Mon, Apr 20, 2020 at 12:48 AM Ingo Molnar <mingo@kernel.org> wrote:
> > >
> > > Fortunately, much of what objtool does against vmlinux.o can be
> > > parallelized in a rather straightforward fashion I believe, if we build
> > > with -ffunction-sections.
> > 
> > Well, I was actually thinking about a simpler model.
> > 
> > By "link time" I didn't mean "after final link". Yes, there may be
> > reasons to do it at that point too (to do any whole-program checks),
> > but that wasn't what I meant.
> > 
> > I meant literally doing it in the $(LD) and $(AR) phases, when you
> > still have lots of independent object files that you are just about to
> > link (or archive - do we even do that any more?) into one.
> > 
> > Then you'd parallelize exactly the same way we do now: one object file
> > at a time, and with no real change of semantics.
> > 
> > IOW, what I was thinking that instead of doing it as part of a final
> > step after the CC/AS, we'd do it as a preparatory step before the
> > LD/AR. Same exact operation, same exact target *.o files, just shifted
> > in time.
> 
> So my pet peeve is that when objtool errors, or crashes, the .o file
> gets deleted and it becomes really hard to debug the situation. I'm
> thinking that your suggestion would actually help with that too.

I do have the same pet peeve and I'm thinking we should just revert
644592d32837 ("objtool: Fail the kernel build on fatal errors") which
would ease most of the pain.  Those fatal errors don't really buy us
much IMO.  Agree?

> I just don't have enough Kbuild foo to even attempt this :/

It's an interesting idea, but it might have its own share of annoyances.

If you added something bad to a file, and just rebuilt that file, you
wouldn't see the objtool warning until later when you build the entire
kernel.  (Of course the same complaint would apply to vmlinux.o
validation.)  But the warning shows the .o file, which could be
confusing.

And for localized testing where you don't want to rebuild everything,
you'd have to figure out which archive belongs to the .o file you want
to run objtool on.  And then rebuilding that archive manually might not
work, for example I have no idea what's going wrong here:

  $ make arch/x86/kernel/built-in.a
    CALL    scripts/checksyscalls.sh
    CALL    scripts/atomic/check-atomics.sh
    DESCEND  objtool
    AR      arch/x86/kernel/built-in.a
  ar: arch/x86/kernel/fpu/built-in.a: No such file or directory
  make[2]: *** [scripts/Makefile.build:387: arch/x86/kernel/built-in.a] Error 1
  make[1]: *** [scripts/Makefile.build:488: arch/x86/kernel] Error 2
  make: *** [Makefile:1723: arch/x86] Error 2


Though I do really like Ingo's idea for parallelizing things for
vmlinux.o.

-- 
Josh

Re: [GIT pull] perf/urgent for 5.7-rc2

[Peter Zijlstra]

On Mon, Apr 20, 2020 at 01:17:30PM -0500, Josh Poimboeuf wrote:
> On Mon, Apr 20, 2020 at 07:40:31PM +0200, Peter Zijlstra wrote:

> > So my pet peeve is that when objtool errors, or crashes, the .o file
> > gets deleted and it becomes really hard to debug the situation. I'm
> > thinking that your suggestion would actually help with that too.
> 
> I do have the same pet peeve and I'm thinking we should just revert
> 644592d32837 ("objtool: Fail the kernel build on fatal errors") which
> would ease most of the pain.  Those fatal errors don't really buy us
> much IMO.  Agree?

Well, I like that it stops the kernel build on an error; I hate that it
makes it so damn hard to then diagnose and fix the error :/

Also, it doesn't really help for crashes, luckily those are somewhat
rare -- except I had one today as a result of a mis-merge...

> > I just don't have enough Kbuild foo to even attempt this :/
> 
> It's an interesting idea, but it might have its own share of annoyances.
> 
> If you added something bad to a file, and just rebuilt that file, you
> wouldn't see the objtool warning until later when you build the entire
> kernel. 

Moo.. :/

Re: [GIT pull] perf/urgent for 5.7-rc2

[Linus Torvalds]

On Mon, Apr 20, 2020 at 11:17 AM Josh Poimboeuf <jpoimboe@redhat.com> wrote:
>
> If you added something bad to a file, and just rebuilt that file, you
> wouldn't see the objtool warning until later when you build the entire
> kernel.

Yes, that's not optimal, but I think I'd personally still prefer that
behavior. Especially since I seldom build single files, and in fact
rather seldom build without some "make -j32" or similar: so build
errors don't happen linearly in the first place.

> (Of course the same complaint would apply to vmlinux.o
> validation.)  But the warning shows the .o file, which could be
> confusing.

The warning should show the proper loe-level *.o file, so I don't see
what's confusing about that.

Yes, the error would happen while trying to link (say)
kernel/built-in.a, and 'make' would report that creating that archive
had failed, but 'objtool' itself would report the particular object
file it was working on that had issues.

So the errors should be pretty obvious. But like PeterZ, the makefile
magic escapes me.

            Linus

Re: [GIT pull] perf/urgent for 5.7-rc2

[Josh Poimboeuf]

On Mon, Apr 20, 2020 at 12:21:46PM -0700, Linus Torvalds wrote:
> On Mon, Apr 20, 2020 at 11:17 AM Josh Poimboeuf <jpoimboe@redhat.com> wrote:
> >
> > If you added something bad to a file, and just rebuilt that file, you
> > wouldn't see the objtool warning until later when you build the entire
> > kernel.
> 
> Yes, that's not optimal, but I think I'd personally still prefer that
> behavior. Especially since I seldom build single files, and in fact
> rather seldom build without some "make -j32" or similar: so build
> errors don't happen linearly in the first place.
> 
> > (Of course the same complaint would apply to vmlinux.o
> > validation.)  But the warning shows the .o file, which could be
> > confusing.
> 
> The warning should show the proper loe-level *.o file, so I don't see
> what's confusing about that.
> 
> Yes, the error would happen while trying to link (say)
> kernel/built-in.a, and 'make' would report that creating that archive
> had failed, but 'objtool' itself would report the particular object
> file it was working on that had issues.

My workflow is often

  $ vi kernel/livepatch/core.c
  $ make kernel/livepatch/core.o

That way I don't have to wait to see what I broke (compile or objtool).

And if whatever I changed was in response to an objtool warning for
kernel/livepatch/core.o, and the warning didn't show up after doing the
above, I might stupidly assume I fixed it.

That's what I meant about it being confusing.  Maybe that's just me
though.

> So the errors should be pretty obvious. But like PeterZ, the makefile
> magic escapes me.

Ditto...

-- 
Josh

Re: [GIT pull] perf/urgent for 5.7-rc2

[pr-tracker-bot]

The pull request you sent on Sun, 19 Apr 2020 13:56:41 -0000:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2020-04-19

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/b7374586ebd48b1bfc75f5ed0eef89de17bdbe04

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

[GIT pull] sched/urgent for 5.7-rc2

[Thomas Gleixner]

Linus,

please pull the latest sched/urgent branch from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched-urgent-2020-04-19

up to:  e0d648f9d883: sched/vtime: Work around an unitialized variable warning


Two fixes for the scheduler:

 - Work around an uninitializaed variable warning where GCC can't figure it
   out.

 - Allow 'isolcpus=' to skip unknown subparameters so that older kernels
   work with the commandline of a newer kernel. Improve the error output
   while at it.

Thanks,

	tglx

------------------>
Borislav Petkov (1):
      sched/vtime: Work around an unitialized variable warning

Peter Xu (1):
      sched/isolation: Allow "isolcpus=" to skip unknown sub-parameters


 kernel/sched/cputime.c   |  4 ++--
 kernel/sched/isolation.c | 21 +++++++++++++++++++--
 2 files changed, 21 insertions(+), 4 deletions(-)

diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index dac9104d126f..ff9435dee1df 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -1003,12 +1003,12 @@ u64 kcpustat_field(struct kernel_cpustat *kcpustat,
 		   enum cpu_usage_stat usage, int cpu)
 {
 	u64 *cpustat = kcpustat->cpustat;
+	u64 val = cpustat[usage];
 	struct rq *rq;
-	u64 val;
 	int err;
 
 	if (!vtime_accounting_enabled_cpu(cpu))
-		return cpustat[usage];
+		return val;
 
 	rq = cpu_rq(cpu);
 
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index 008d6ac2342b..808244f3ddd9 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -149,6 +149,9 @@ __setup("nohz_full=", housekeeping_nohz_full_setup);
 static int __init housekeeping_isolcpus_setup(char *str)
 {
 	unsigned int flags = 0;
+	bool illegal = false;
+	char *par;
+	int len;
 
 	while (isalpha(*str)) {
 		if (!strncmp(str, "nohz,", 5)) {
@@ -169,8 +172,22 @@ static int __init housekeeping_isolcpus_setup(char *str)
 			continue;
 		}
 
-		pr_warn("isolcpus: Error, unknown flag\n");
-		return 0;
+		/*
+		 * Skip unknown sub-parameter and validate that it is not
+		 * containing an invalid character.
+		 */
+		for (par = str, len = 0; *str && *str != ','; str++, len++) {
+			if (!isalpha(*str) && *str != '_')
+				illegal = true;
+		}
+
+		if (illegal) {
+			pr_warn("isolcpus: Invalid flag %.*s\n", len, par);
+			return 0;
+		}
+
+		pr_info("isolcpus: Skipped unknown flag %.*s\n", len, par);
+		str++;
 	}
 
 	/* Default behaviour for isolcpus without flags */

Re: [GIT pull] sched/urgent for 5.7-rc2

[pr-tracker-bot]

The pull request you sent on Sun, 19 Apr 2020 13:56:42 -0000:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched-urgent-2020-04-19

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/08dd3872770b78d3d5e26d251b5853aa26e35d41

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

[GIT pull] timers/urgent for 5.7-rc2

[Thomas Gleixner]

Linus,

please pull the latest timers/urgent branch from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers-urgent-2020-04-19

up to:  94d440d61846: proc, time/namespace: Show clock symbolic names in /proc/pid/timens_offsets


An update for the proc interface of time namespaces: Use symbolic names
instead of clockid numbers. The usability nuisance of numbers was noticed
by Michael when polishing the man page.

Thanks,

	tglx

------------------>
Andrei Vagin (1):
      proc, time/namespace: Show clock symbolic names in /proc/pid/timens_offsets


 fs/proc/base.c          | 14 +++++++++++++-
 kernel/time/namespace.c | 15 ++++++++++++++-
 2 files changed, 27 insertions(+), 2 deletions(-)

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 6042b646ab27..572898dd16a0 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1573,6 +1573,7 @@ static ssize_t timens_offsets_write(struct file *file, const char __user *buf,
 	noffsets = 0;
 	for (pos = kbuf; pos; pos = next_line) {
 		struct proc_timens_offset *off = &offsets[noffsets];
+		char clock[10];
 		int err;
 
 		/* Find the end of line and ensure we don't look past it */
@@ -1584,10 +1585,21 @@ static ssize_t timens_offsets_write(struct file *file, const char __user *buf,
 				next_line = NULL;
 		}
 
-		err = sscanf(pos, "%u %lld %lu", &off->clockid,
+		err = sscanf(pos, "%9s %lld %lu", clock,
 				&off->val.tv_sec, &off->val.tv_nsec);
 		if (err != 3 || off->val.tv_nsec >= NSEC_PER_SEC)
 			goto out;
+
+		clock[sizeof(clock) - 1] = 0;
+		if (strcmp(clock, "monotonic") == 0 ||
+		    strcmp(clock, __stringify(CLOCK_MONOTONIC)) == 0)
+			off->clockid = CLOCK_MONOTONIC;
+		else if (strcmp(clock, "boottime") == 0 ||
+			 strcmp(clock, __stringify(CLOCK_BOOTTIME)) == 0)
+			off->clockid = CLOCK_BOOTTIME;
+		else
+			goto out;
+
 		noffsets++;
 		if (noffsets == ARRAY_SIZE(offsets)) {
 			if (next_line)
diff --git a/kernel/time/namespace.c b/kernel/time/namespace.c
index 3b30288793fe..53bce347cd50 100644
--- a/kernel/time/namespace.c
+++ b/kernel/time/namespace.c
@@ -338,7 +338,20 @@ static struct user_namespace *timens_owner(struct ns_common *ns)
 
 static void show_offset(struct seq_file *m, int clockid, struct timespec64 *ts)
 {
-	seq_printf(m, "%d %lld %ld\n", clockid, ts->tv_sec, ts->tv_nsec);
+	char *clock;
+
+	switch (clockid) {
+	case CLOCK_BOOTTIME:
+		clock = "boottime";
+		break;
+	case CLOCK_MONOTONIC:
+		clock = "monotonic";
+		break;
+	default:
+		clock = "unknown";
+		break;
+	}
+	seq_printf(m, "%-10s %10lld %9ld\n", clock, ts->tv_sec, ts->tv_nsec);
 }
 
 void proc_timens_show_offsets(struct task_struct *p, struct seq_file *m)

Re: [GIT pull] timers/urgent for 5.7-rc2

[pr-tracker-bot]

The pull request you sent on Sun, 19 Apr 2020 13:56:43 -0000:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers-urgent-2020-04-19

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/3e0dea57686d8a0cb8b870de0f5ccbd2e941d8b3

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

[GIT pull] x86/urgent for 5.7-rc2

[Thomas Gleixner]

Linus,

please pull the latest x86/urgent branch from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86-urgent-2020-04-19

up to:  8b9a18a9f249: x86/split_lock: Add Tremont family CPU models


A set of fixes for x86 and objtool:

 objtool:
 
  - Ignore the double UD2 which is emitted in BUG() when CONFIG_UBSAN_TRAP
    is enabled.

  - Support clang non-section symbols in objtool ORC dump

  - Fix switch table detection in .text.unlikely

  - Make the BP scratch register warning more robust.

 x86:

  - Increase microcode maximum patch size for AMD to cope with new CPUs
    which have a larger patch size.

  - Fix a crash in the resource control filesystem when the removal of the
    default resource group is attempted.

  - Preserve Code and Data Prioritization enabled state accross CPU
    hotplug.

  - Update split lock cpu matching to use the new X86_MATCH macros.

  - Change the split lock enumeration as Intel finaly decided that the
    IA32_CORE_CAPABILITIES bits are not architectural contrary to what
    the SDM claims. !@#%$^!

  - Add Tremont CPU models to the split lock detection cpu match.

  - Add a missing static attribute to make sparse happy.

Thanks,

	tglx

------------------>
James Morse (1):
      x86/resctrl: Preserve CDP enable over CPU hotplug

Jason Yan (1):
      x86/umip: Make umip_insns static

John Allen (1):
      x86/microcode/AMD: Increase microcode PATCH_MAX_SIZE

Josh Poimboeuf (5):
      objtool: Fix CONFIG_UBSAN_TRAP unreachable warnings
      objtool: Support Clang non-section symbols in ORC dump
      objtool: Support Clang non-section symbols in ORC generation
      objtool: Fix switch table detection in .text.unlikely
      objtool: Make BP scratch register warning more robust

Reinette Chatre (1):
      x86/resctrl: Fix invalid attempt at removing the default resource group

Tony Luck (3):
      x86/split_lock: Update to use X86_MATCH_INTEL_FAM6_MODEL()
      x86/split_lock: Bits in IA32_CORE_CAPABILITIES are not architectural
      x86/split_lock: Add Tremont family CPU models


 arch/x86/include/asm/microcode_amd.h   |  2 +-
 arch/x86/kernel/cpu/intel.c            | 54 ++++++++++++++++++++++------------
 arch/x86/kernel/cpu/resctrl/core.c     |  2 ++
 arch/x86/kernel/cpu/resctrl/internal.h |  1 +
 arch/x86/kernel/cpu/resctrl/rdtgroup.c | 16 +++++++++-
 arch/x86/kernel/umip.c                 |  2 +-
 tools/objtool/check.c                  | 26 +++++++++++-----
 tools/objtool/orc_dump.c               | 44 ++++++++++++++++-----------
 tools/objtool/orc_gen.c                | 33 ++++++++++++++++-----
 9 files changed, 127 insertions(+), 53 deletions(-)

diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h
index 6685e1218959..7063b5a43220 100644
--- a/arch/x86/include/asm/microcode_amd.h
+++ b/arch/x86/include/asm/microcode_amd.h
@@ -41,7 +41,7 @@ struct microcode_amd {
 	unsigned int			mpb[0];
 };
 
-#define PATCH_MAX_SIZE PAGE_SIZE
+#define PATCH_MAX_SIZE (3 * PAGE_SIZE)
 
 #ifdef CONFIG_MICROCODE_AMD
 extern void __init load_ucode_amd_bsp(unsigned int family);
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index bf08d4508ecb..a19a680542ce 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -1119,35 +1119,53 @@ void switch_to_sld(unsigned long tifn)
 	sld_update_msr(!(tifn & _TIF_SLD));
 }
 
-#define SPLIT_LOCK_CPU(model) {X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY}
-
 /*
- * The following processors have the split lock detection feature. But
- * since they don't have the IA32_CORE_CAPABILITIES MSR, the feature cannot
- * be enumerated. Enable it by family and model matching on these
- * processors.
+ * Bits in the IA32_CORE_CAPABILITIES are not architectural, so they should
+ * only be trusted if it is confirmed that a CPU model implements a
+ * specific feature at a particular bit position.
+ *
+ * The possible driver data field values:
+ *
+ * - 0: CPU models that are known to have the per-core split-lock detection
+ *	feature even though they do not enumerate IA32_CORE_CAPABILITIES.
+ *
+ * - 1: CPU models which may enumerate IA32_CORE_CAPABILITIES and if so use
+ *      bit 5 to enumerate the per-core split-lock detection feature.
  */
 static const struct x86_cpu_id split_lock_cpu_ids[] __initconst = {
-	SPLIT_LOCK_CPU(INTEL_FAM6_ICELAKE_X),
-	SPLIT_LOCK_CPU(INTEL_FAM6_ICELAKE_L),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X,		0),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L,		0),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT,	1),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D,	1),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_L,	1),
 	{}
 };
 
 void __init cpu_set_core_cap_bits(struct cpuinfo_x86 *c)
 {
-	u64 ia32_core_caps = 0;
+	const struct x86_cpu_id *m;
+	u64 ia32_core_caps;
+
+	if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
+		return;
 
-	if (c->x86_vendor != X86_VENDOR_INTEL)
+	m = x86_match_cpu(split_lock_cpu_ids);
+	if (!m)
 		return;
-	if (cpu_has(c, X86_FEATURE_CORE_CAPABILITIES)) {
-		/* Enumerate features reported in IA32_CORE_CAPABILITIES MSR. */
+
+	switch (m->driver_data) {
+	case 0:
+		break;
+	case 1:
+		if (!cpu_has(c, X86_FEATURE_CORE_CAPABILITIES))
+			return;
 		rdmsrl(MSR_IA32_CORE_CAPS, ia32_core_caps);
-	} else if (!boot_cpu_has(X86_FEATURE_HYPERVISOR)) {
-		/* Enumerate split lock detection by family and model. */
-		if (x86_match_cpu(split_lock_cpu_ids))
-			ia32_core_caps |= MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT;
+		if (!(ia32_core_caps & MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT))
+			return;
+		break;
+	default:
+		return;
 	}
 
-	if (ia32_core_caps & MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT)
-		split_lock_setup();
+	split_lock_setup();
 }
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 89049b343c7a..d8cc5223b7ce 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -578,6 +578,8 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 	d->id = id;
 	cpumask_set_cpu(cpu, &d->cpu_mask);
 
+	rdt_domain_reconfigure_cdp(r);
+
 	if (r->alloc_capable && domain_setup_ctrlval(r, d)) {
 		kfree(d);
 		return;
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 181c992f448c..3dd13f3a8b23 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -601,5 +601,6 @@ bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d);
 void __check_limbo(struct rdt_domain *d, bool force_free);
 bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r);
 bool cbm_validate_amd(char *buf, u32 *data, struct rdt_resource *r);
+void rdt_domain_reconfigure_cdp(struct rdt_resource *r);
 
 #endif /* _ASM_X86_RESCTRL_INTERNAL_H */
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 064e9ef44cd6..5a359d9fcc05 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -1859,6 +1859,19 @@ static int set_cache_qos_cfg(int level, bool enable)
 	return 0;
 }
 
+/* Restore the qos cfg state when a domain comes online */
+void rdt_domain_reconfigure_cdp(struct rdt_resource *r)
+{
+	if (!r->alloc_capable)
+		return;
+
+	if (r == &rdt_resources_all[RDT_RESOURCE_L2DATA])
+		l2_qos_cfg_update(&r->alloc_enabled);
+
+	if (r == &rdt_resources_all[RDT_RESOURCE_L3DATA])
+		l3_qos_cfg_update(&r->alloc_enabled);
+}
+
 /*
  * Enable or disable the MBA software controller
  * which helps user specify bandwidth in MBps.
@@ -3072,7 +3085,8 @@ static int rdtgroup_rmdir(struct kernfs_node *kn)
 	 * If the rdtgroup is a mon group and parent directory
 	 * is a valid "mon_groups" directory, remove the mon group.
 	 */
-	if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn) {
+	if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn &&
+	    rdtgrp != &rdtgroup_default) {
 		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
 		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
 			ret = rdtgroup_ctrl_remove(kn, rdtgrp);
diff --git a/arch/x86/kernel/umip.c b/arch/x86/kernel/umip.c
index 4d732a444711..8d5cbe1bbb3b 100644
--- a/arch/x86/kernel/umip.c
+++ b/arch/x86/kernel/umip.c
@@ -81,7 +81,7 @@
 #define	UMIP_INST_SLDT  3       /* 0F 00 /0 */
 #define	UMIP_INST_STR   4       /* 0F 00 /1 */
 
-const char * const umip_insns[5] = {
+static const char * const umip_insns[5] = {
 	[UMIP_INST_SGDT] = "SGDT",
 	[UMIP_INST_SIDT] = "SIDT",
 	[UMIP_INST_SMSW] = "SMSW",
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 8dd01f986fbb..4b170fd08a28 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -1050,10 +1050,7 @@ static struct rela *find_jump_table(struct objtool_file *file,
 	 * it.
 	 */
 	for (;
-	     &insn->list != &file->insn_list &&
-	     insn->sec == func->sec &&
-	     insn->offset >= func->offset;
-
+	     &insn->list != &file->insn_list && insn->func && insn->func->pfunc == func;
 	     insn = insn->first_jump_src ?: list_prev_entry(insn, list)) {
 
 		if (insn != orig_insn && insn->type == INSN_JUMP_DYNAMIC)
@@ -2008,8 +2005,8 @@ static int validate_return(struct symbol *func, struct instruction *insn, struct
 	}
 
 	if (state->bp_scratch) {
-		WARN("%s uses BP as a scratch register",
-		     func->name);
+		WARN_FUNC("BP used as a scratch register",
+			  insn->sec, insn->offset);
 		return 1;
 	}
 
@@ -2364,14 +2361,27 @@ static bool ignore_unreachable_insn(struct instruction *insn)
 	    !strcmp(insn->sec->name, ".altinstr_aux"))
 		return true;
 
+	if (!insn->func)
+		return false;
+
+	/*
+	 * CONFIG_UBSAN_TRAP inserts a UD2 when it sees
+	 * __builtin_unreachable().  The BUG() macro has an unreachable() after
+	 * the UD2, which causes GCC's undefined trap logic to emit another UD2
+	 * (or occasionally a JMP to UD2).
+	 */
+	if (list_prev_entry(insn, list)->dead_end &&
+	    (insn->type == INSN_BUG ||
+	     (insn->type == INSN_JUMP_UNCONDITIONAL &&
+	      insn->jump_dest && insn->jump_dest->type == INSN_BUG)))
+		return true;
+
 	/*
 	 * Check if this (or a subsequent) instruction is related to
 	 * CONFIG_UBSAN or CONFIG_KASAN.
 	 *
 	 * End the search at 5 instructions to avoid going into the weeds.
 	 */
-	if (!insn->func)
-		return false;
 	for (i = 0; i < 5; i++) {
 
 		if (is_kasan_insn(insn) || is_ubsan_insn(insn))
diff --git a/tools/objtool/orc_dump.c b/tools/objtool/orc_dump.c
index 13ccf775a83a..ba4cbb1cdd63 100644
--- a/tools/objtool/orc_dump.c
+++ b/tools/objtool/orc_dump.c
@@ -66,7 +66,7 @@ int orc_dump(const char *_objname)
 	char *name;
 	size_t nr_sections;
 	Elf64_Addr orc_ip_addr = 0;
-	size_t shstrtab_idx;
+	size_t shstrtab_idx, strtab_idx = 0;
 	Elf *elf;
 	Elf_Scn *scn;
 	GElf_Shdr sh;
@@ -127,6 +127,8 @@ int orc_dump(const char *_objname)
 
 		if (!strcmp(name, ".symtab")) {
 			symtab = data;
+		} else if (!strcmp(name, ".strtab")) {
+			strtab_idx = i;
 		} else if (!strcmp(name, ".orc_unwind")) {
 			orc = data->d_buf;
 			orc_size = sh.sh_size;
@@ -138,7 +140,7 @@ int orc_dump(const char *_objname)
 		}
 	}
 
-	if (!symtab || !orc || !orc_ip)
+	if (!symtab || !strtab_idx || !orc || !orc_ip)
 		return 0;
 
 	if (orc_size % sizeof(*orc) != 0) {
@@ -159,21 +161,29 @@ int orc_dump(const char *_objname)
 				return -1;
 			}
 
-			scn = elf_getscn(elf, sym.st_shndx);
-			if (!scn) {
-				WARN_ELF("elf_getscn");
-				return -1;
-			}
-
-			if (!gelf_getshdr(scn, &sh)) {
-				WARN_ELF("gelf_getshdr");
-				return -1;
-			}
-
-			name = elf_strptr(elf, shstrtab_idx, sh.sh_name);
-			if (!name || !*name) {
-				WARN_ELF("elf_strptr");
-				return -1;
+			if (GELF_ST_TYPE(sym.st_info) == STT_SECTION) {
+				scn = elf_getscn(elf, sym.st_shndx);
+				if (!scn) {
+					WARN_ELF("elf_getscn");
+					return -1;
+				}
+
+				if (!gelf_getshdr(scn, &sh)) {
+					WARN_ELF("gelf_getshdr");
+					return -1;
+				}
+
+				name = elf_strptr(elf, shstrtab_idx, sh.sh_name);
+				if (!name) {
+					WARN_ELF("elf_strptr");
+					return -1;
+				}
+			} else {
+				name = elf_strptr(elf, strtab_idx, sym.st_name);
+				if (!name) {
+					WARN_ELF("elf_strptr");
+					return -1;
+				}
 			}
 
 			printf("%s+%llx:", name, (unsigned long long)rela.r_addend);
diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c
index 41e4a2754da4..4c0dabd28000 100644
--- a/tools/objtool/orc_gen.c
+++ b/tools/objtool/orc_gen.c
@@ -88,11 +88,6 @@ static int create_orc_entry(struct elf *elf, struct section *u_sec, struct secti
 	struct orc_entry *orc;
 	struct rela *rela;
 
-	if (!insn_sec->sym) {
-		WARN("missing symbol for section %s", insn_sec->name);
-		return -1;
-	}
-
 	/* populate ORC data */
 	orc = (struct orc_entry *)u_sec->data->d_buf + idx;
 	memcpy(orc, o, sizeof(*orc));
@@ -105,8 +100,32 @@ static int create_orc_entry(struct elf *elf, struct section *u_sec, struct secti
 	}
 	memset(rela, 0, sizeof(*rela));
 
-	rela->sym = insn_sec->sym;
-	rela->addend = insn_off;
+	if (insn_sec->sym) {
+		rela->sym = insn_sec->sym;
+		rela->addend = insn_off;
+	} else {
+		/*
+		 * The Clang assembler doesn't produce section symbols, so we
+		 * have to reference the function symbol instead:
+		 */
+		rela->sym = find_symbol_containing(insn_sec, insn_off);
+		if (!rela->sym) {
+			/*
+			 * Hack alert.  This happens when we need to reference
+			 * the NOP pad insn immediately after the function.
+			 */
+			rela->sym = find_symbol_containing(insn_sec,
+							   insn_off - 1);
+		}
+		if (!rela->sym) {
+			WARN("missing symbol for insn at offset 0x%lx\n",
+			     insn_off);
+			return -1;
+		}
+
+		rela->addend = insn_off - rela->sym->offset;
+	}
+
 	rela->type = R_X86_64_PC32;
 	rela->offset = idx * sizeof(int);
 	rela->sec = ip_relasec;

Re: [GIT pull] x86/urgent for 5.7-rc2

[pr-tracker-bot]

The pull request you sent on Sun, 19 Apr 2020 13:56:44 -0000:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86-urgent-2020-04-19

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/0fe5f9ca223573167c4c4156903d751d2c8e160e

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

Re: [GIT pull] core/urgent for 5.7-rc2

[pr-tracker-bot]

The pull request you sent on Sun, 19 Apr 2020 13:56:38 -0000:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git core-urgent-2020-04-19

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/5e7de581270d26869a4ef47c957c667e57372d79

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker